The team has a dual mandate: maximizing compute efficiency to serve our explosive customer growth, while enabling breakthrough research by giving our scientists the high-performance inference infrastructure they need to develop next-generation models. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms.

Strong candidates may also have experience with:

• High-performance, large-scale distributed systems
• Implementing and deploying machine learning systems at scale
• Load balancing, request routing, or traffic management systems
• LLM inference optimization, batching, and caching strategies
• Kubernetes and cloud infrastructure (AWS, GCP)
• Python or Rust

You may be a good fit if you:

• Have significant software engineering experience, particularly with distributed systems
• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Want to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Representative projects across the org:

• Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
• Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
• Building production-grade deployment pipelines for releasing new models to millions of users
• Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
• Contributing to new inference features (e.g., structured sampling, prompt caching)
• Supporting inference for new model architectures
• Analyzing observability data to tune performance based on real-world production workloads
• Managing multi-region deployments and geographic routing for global customers

Deadline to apply: None. Applications will be reviewed on a rolling basis.

The annual compensation range for this role is £225,000-£325,000 GBP.

XML job scraping automation by YubHub

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.

The team has a dual mandate: maximizing compute efficiency to serve our explosive customer growth, while enabling breakthrough research by giving our scientists the high-performance inference infrastructure they need to develop next-generation models. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms.

Strong candidates may also have experience with:

• High-performance, large-scale distributed systems
• Implementing and deploying machine learning systems at scale
• Load balancing, request routing, or traffic management systems
• LLM inference optimization, batching, and caching strategies
• Kubernetes and cloud infrastructure (AWS, GCP)
• Python or Rust

You may be a good fit if you:

• Have significant software engineering experience, particularly with distributed systems
• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Want to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Representative projects across the org:

• Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
• Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
• Building production-grade deployment pipelines for releasing new models to millions of users
• Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
• Contributing to new inference features (e.g., structured sampling, prompt caching)
• Supporting inference for new model architectures
• Analyzing observability data to tune performance based on real-world production workloads
• Managing multi-region deployments and geographic routing for global customers

Annual compensation range for this role is €235,000-€295,000 EUR.

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links,visit anthropic.com/careers directly for confirmed position openings.

How we're different:

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact , advancing our long-term goals of steerable, trustworthy AI , rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.

XML job scraping automation by YubHub

XML job scraping automation by YubHub

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.

As a Staff Software Engineer on our Inference team, you will work end to end, identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research. Strong candidates should have familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching strategies, and multi-accelerator deployments is highly encouraged but not strictly necessary.

Responsibilities:

• Work end to end on identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research
• Collaborate with the team to design and implement solutions to complex problems
• Develop and maintain large-scale distributed systems
• Implement and deploy machine learning systems at scale
• Load balancing, request routing, or traffic management systems
• LLM inference optimization, batching, and caching strategies
• Kubernetes and cloud infrastructure (AWS, GCP)
• Python or Rust

Requirements:

• Significant software engineering experience, particularly with distributed systems
• Results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Want to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Benefits:

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space in which to collaborate with colleagues

Application Instructions:

If you're interested in this role, please submit your application through our website. We look forward to hearing from you!

XML job scraping automation by YubHub

Your work will touch the full GenAI inference stack , from kernels and runtimes to orchestration and memory management. You will contribute to the design and implementation of the inference engine, and collaborate on model-serving stack optimized for large-scale LLMs inference.

Key responsibilities include:

• Collaborating with researchers to bring new model architectures or features (sparsity, activation compression, mixture-of-experts) into the engine
• Optimizing for latency, throughput, memory efficiency, and hardware utilization across GPUs, and accelerators
• Building and maintaining instrumentation, profiling, and tracing tooling to uncover bottlenecks and guide optimizations
• Developing and enhancing scalable routing, batching, scheduling, memory management, and dynamic loading mechanisms for inference workloads
• Supporting reliability, reproducibility, and fault tolerance in the inference pipelines, including A/B launches, rollback, and model versioning
• Integrating with federated, distributed inference infrastructure – orchestrate across nodes, balance load, handle communication overhead
• Collaborating cross-functionally: with platform engineers, cloud infrastructure, and security/compliance teams
• Documenting and sharing learnings, contributing to internal best practices and open-source efforts when possible

Requirements include:

• BS/MS/PhD in Computer Science, or a related field
• Strong software engineering background (3+ years or equivalent) in performance-critical systems
• Solid understanding of ML inference internals: attention, MLPs, recurrent modules, quantization, sparse operations, etc.
• Hands-on experience with CUDA, GPU programming, and key libraries (cuBLAS, cuDNN, NCCL, etc.)
• Comfortable designing and operating distributed systems, including RPC frameworks, queuing, RPC batching, sharding, memory partitioning
• Demonstrated ability to uncover and solve performance bottlenecks across layers (kernel, memory, networking, scheduler)
• Experience building instrumentation, tracing, and profiling tools for ML models
• Ability to work closely with ML researchers, translate novel model ideas into production systems
• Ownership mindset and eagerness to dive deep into complex system challenges
• Bonus: published research or open-source contributions in ML systems, inference optimization, or model serving

XML job scraping automation by YubHub

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.

As a Staff Software Engineer on our Inference team, you will work end to end, identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research. Strong candidates should have familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching strategies, and multi-accelerator deployments is highly encouraged but not strictly necessary.

Strong candidates may also have experience with

• High-performance, large-scale distributed systems
• Implementing and deploying machine learning systems at scale
• Load balancing, request routing, or traffic management systems
• LLM inference optimization, batching, and caching strategies
• Kubernetes and cloud infrastructure (AWS, GCP)
• Python or Rust

You may be a good fit if you

• Have significant software engineering experience, particularly with distributed systems
• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Want to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Representative projects across the org

• Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
• Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
• Building production-grade deployment pipelines for releasing new models to millions of users
• Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
• Contributing to new inference features (e.g., structured sampling, prompt caching)
• Supporting inference for new model architectures
• Analyzing observability data to tune performance based on real-world production workloads
• Managing multi-region deployments and geographic routing for global customers

Deadline to apply

None. Applications will be reviewed on a rolling basis.

Annual compensation range

The annual compensation range for this role is £325,000-£390,000 GBP.

Logistics

• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
• Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position
• Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
• Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

Why work with us?

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact , advancing our long-term goals of steerable, trustworthy AI , rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.

XML job scraping automation by YubHub

About the Role:

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.

The team has a dual mandate: maximizing compute efficiency to serve our explosive customer growth, while enabling breakthrough research by giving our scientists the high-performance inference infrastructure they need to develop next-generation models. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms.

Responsibilities:

• Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
• Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
• Building production-grade deployment pipelines for releasing new models to millions of users
• Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
• Contributing to new inference features (e.g., structured sampling, prompt caching)
• Supporting inference for new model architectures
• Analyzing observability data to tune performance based on real-world production workloads
• Managing multi-region deployments and geographic routing for global customers

Requirements:

• Significant software engineering experience, particularly with distributed systems
• Results-oriented, with a bias towards flexibility and impact
• Ability to pick up slack, even if it goes outside your job description
• Willingness to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Benefits:

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space in which to collaborate with colleagues

Note: The salary range for this role is €235,000-€295,000 EUR per year.

XML job scraping automation by YubHub

Key responsibilities include:

• Leading design reviews and driving architecture within the team
• Defining and owning SLIs/SLOs and ensuring post-incident actions land and reliability improves release-over-release
• Implementing advanced optimizations such as micro-batch schedulers, speculative decoding, and KV-cache reuse
• Strengthening incident posture through capacity planning, autoscaling policy, and rollback/traffic-shift strategies
• Mentoring IC1/IC2 engineers and reviewing cross-team designs to elevate coding/testing standards

We're looking for someone with strong coding skills in Python or Go, deep familiarity with networked systems and performance, and hands-on experience with Kubernetes at production scale. If you have experience with inference internals, batching, caching, mixed precision, and streaming token delivery, that's a plus.

In addition to a competitive salary, we offer a range of benefits including medical, dental, and vision insurance, company-paid life insurance, and flexible PTO. We're committed to creating a work environment that's inclusive, diverse, and supportive of our employees' well-being.

XML job scraping automation by YubHub

Key responsibilities include:

• Lead design reviews and drive architecture within the team; decompose multi-service work into clear milestones.
• Define and own SLIs/SLOs; ensure post-incident actions land and reliability improves release-over-release.
• Implement advanced optimizations (e.g., micro-batch schedulers, speculative decoding, KV-cache reuse) and quantify impact.
• Strengthen incident posture: capacity planning, autoscaling policy, graceful degradation, rollback/traffic-shift strategies.
• Mentor IC1/IC2 engineers; review cross-team designs and elevate coding/testing standards.

Requirements include:

• 3-5 years of industry experience building distributed systems or cloud services.
• Strong coding in Python or Go (C++ a plus) and deep familiarity with networked systems and performance.
• Hands-on experience with Kubernetes at production scale, CI/CD, and observability stacks (Prometheus, Grafana, OpenTelemetry).
• Practical knowledge of inference internals: batching, caching, mixed precision (BF16/FP8), streaming token delivery.
• Proven track record improving tail latency (P95/P99) and service reliability through metrics-driven work.

Preferred qualifications include contributions to inference frameworks, experience with CUDA kernels, NCCL/SHARP, RDMA/NUMA, or GPU interconnect topologies, and leading multi-team initiatives or partnering with customers on mission-critical launches.

XML job scraping automation by YubHub

On this team, you will build and operate the ML infrastructure and product services that enable trust and intelligence across Plaid's network. You'll own feature engineering, offline training and batch scoring, online feature serving, and real-time inference so model outputs directly power partner-facing fraud & trust products and bank intelligence features.

Responsibilities

• Embed model inference into Network Enablement product flows and decision logic (APIs, feature flags, backend flows).
• Define and instrument product + ML success metrics (fraud reduction, retention lift, false positives, downstream impact).
• Design and run experiments and rollout plans (backtesting, shadow scoring, A/B tests, feature-flagged releases) to validate product hypotheses.
• Build and operate offline training pipelines and production batch scoring for bank intelligence products.
• Ship and maintain online feature serving and low-latency model inference endpoints for real-time partner/bank scoring.
• Implement model CI/CD, model/version registry, and safe rollout/rollback strategies.
• Monitor model/data health: drift/regression detection, model-quality dashboards, alerts, and SLOs targeted to partner product needs.
• Ensure offline and online parity, data lineage, and automated validation / data contracts to reduce regressions.
• Optimize inference performance and cost for real-time scoring (batching, caching, runtime selection).
• Ensure fairness, explainability and PII-aware handling for partner-facing ML features; maintain auditability for compliance.
• Partner with platform and cross-functional teams to scale the ML/data foundation (graph features, sequence embeddings, unified pipelines).
• Mentor engineers and document team standards for ML productization and operations.

Qualifications

• Must-haves:
• Strong software engineering skills including systems design, APIs, and building reliable backend services (Go or Python preferred).
• Production experience with batch and streaming data pipelines and orchestration tools such as Airflow or Spark.
• Experience building or operating real-time scoring and online feature-serving systems, including feature stores and low-latency model inference.
• Experience integrating model outputs into product flows (APIs, feature flags) and measuring impact through experiments and product metrics.
• Experience with model lifecycle and operations: model registries, CI/CD for models, reproducible training, offline & online parity, monitoring and incident response.
• Nice to have:
• Experience in fraud, risk, or marketing intelligence domains.
• Experience with feature-store products (Tecton / Chronon / Feast / internal) and unified pipelines.
• Experience with graph frameworks, graph feature engineering, or sequence embeddings.
• Experience optimizing inference at scale (Triton/ONNX/quantization, batching, caching).

Additional Information

Our mission at Plaid is to unlock financial freedom for everyone. To support that mission, we seek to build a diverse team of driven individuals who care deeply about making the financial ecosystem more equitable.

XML job scraping automation by YubHub

The Cloud Inference team scales and optimizes Claude to serve the massive audiences of developers and enterprise companies across AWS, GCP, Azure, and future cloud service providers (CSPs). We own the end-to-end product of Claude on each cloud platform—from API integration and intelligent request routing to inference execution, capacity management, and day-to-day operations.

Our engineers are extremely high leverage: we simultaneously drive multiple major revenue streams while optimizing one of Anthropic's most precious resources—compute. As we expand to more cloud platforms, the complexity of managing inference efficiently across providers with different hardware, networking stacks, and operational models grows significantly. We need engineers who can navigate these platform differences, build robust abstractions that work across providers, and make smart infrastructure decisions that keep us cost-effective at massive scale.

Your work will increase the scale at which our services operate, accelerate our ability to reliably launch new frontier models and innovative features to customers across all platforms, and ensure our LLMs meet rigorous safety, performance, and security standards.

What You'll Do

• Design and build infrastructure that serves Claude across multiple CSPs, accounting for differences in compute hardware, networking, APIs, and operational models
• Collaborate with CSP partner engineering teams to resolve operational issues, influence provider roadmaps, and stand up end-to-end serving on new cloud platforms
• Design and evolve CI/CD automation systems, including validation and deployment pipelines, that reliably ship new model versions to millions of users across cloud platforms without regressions
• Design interfaces and tooling abstractions across CSPs that enable cost-effective inference management, scale across providers, and reduce per-platform complexity
• Contribute to capacity planning and autoscaling strategies that dynamically match supply with demand across CSP validation and production workloads
• Optimize inference cost and performance across providers—designing workload placement and routing systems that direct requests to the most cost-effective accelerator and region
• Contribute to inference features that must work consistently across all platforms
• Analyze observability data across providers to identify performance bottlenecks, cost anomalies, and regressions, and drive remediation based on real-world production workloads

You May Be a Good Fit If You:

• Have significant software engineering experience, with a strong background in high-performance, large-scale distributed systems serving millions of users
• Have experience building or operating services on at least one major cloud platform (AWS, GCP, or Azure), with exposure to Kubernetes, Infrastructure as Code or container orchestration
• Have strong interest in inference
• Thrive in cross-functional collaboration with both internal teams and external partners
• Are a fast learner who can quickly ramp up on new technologies, hardware platforms, and provider ecosystems
• Are highly autonomous and self-driven, taking ownership of problems end-to-end with a bias toward flexibility and high-impact work
• Pick up slack, even when it goes outside your job description

Strong Candidates May Also Have Experience With

• Direct experience working with CSP partner teams to scale infrastructure or products across multiple platforms, navigating differences in networking, security, privacy, billing, and managed service offerings
• A background in building platform-agnostic tooling or abstraction layers that work across cloud providers
• Hands-on experience with capacity management, cost optimization, or resource planning at scale across heterogeneous environments
• Strong familiarity with LLM inference optimization, batching, caching, and serving strategies
• Experience with Machine learning infrastructure including GPUs, TPUs, Trainium, or other AI accelerators
• Background designing and building CI/CD systems that automate deployment and validation across cloud environments
• Solid understanding of multi-region deployments, geographic routing, and global traffic management
• Proficiency in Python or Rust

Logistics

Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience. Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

XML job scraping automation by YubHub

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators. The team has a dual mandate: maximizing compute efficiency to serve our explosive customer growth, while enabling breakthrough research by giving our scientists the high-performance inference infrastructure they need to develop next-generation models. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms.

As a Staff Software Engineer on our Inference team, you will work end to end, identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research. Strong candidates should have familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching strategies, and multi-accelerator deployments is highly encouraged but not strictly necessary.

Strong candidates may also have experience with

• High-performance, large-scale distributed systems
• Implementing and deploying machine learning systems at scale
• Load balancing, request routing, or traffic management systems
• LLM inference optimization, batching, and caching strategies
• Kubernetes and cloud infrastructure (AWS, GCP)
• Python or Rust

You may be a good fit if you

• Have significant software engineering experience, particularly with distributed systems
• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Want to learn more about machine learning systems and infrastructure
• Thrive in environments where technical excellence directly drives both business results and research breakthroughs
• Care about the societal impacts of your work

Representative projects across the org

• Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
• Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
• Building production-grade deployment pipelines for releasing new models to millions of users
• Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
• Contributing to new inference features (e.g., structured sampling, prompt caching)
• Supporting inference for new model architectures
• Analyzing observability data to tune performance based on real-world production workloads
• Managing multi-region deployments and geographic routing for global customers

Deadline to apply: None. Applications will be reviewed on a rolling basis.

Logistics

• Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.
• Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
• Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view

XML job scraping automation by YubHub

What you'll do

As an AI Inference Engineer at Perplexity, you will have the opportunity to work on large-scale deployment of machine learning models for real-time inference. You will be responsible for developing APIs for AI inference that will be used by both internal and external customers.

• Develop APIs for AI inference that will be used by both internal and external customers
• Benchmark and address bottlenecks throughout our inference stack
• Improve the reliability and observability of our systems and respond to system outages
• Explore novel research and implement LLM inference optimisations

What you need

To be successful in this role, you will need to have experience with ML systems and deep learning frameworks (e.g. PyTorch, TensorFlow, ONNX), familiarity with common LLM architectures and inference optimisation techniques (e.g. continuous batching, quantisation, etc.), and understanding of GPU architectures or experience with GPU kernel programming using CUDA.

• Experience with ML systems and deep learning frameworks (e.g. PyTorch, TensorFlow, ONNX)
• Familiarity with common LLM architectures and inference optimisation techniques (e.g. continuous batching, quantisation, etc.)
• Understanding of GPU architectures or experience with GPU kernel programming using CUDA

XML job scraping automation by YubHub