{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/weaviate"},"x-facet":{"type":"skill","slug":"weaviate","display":"Weaviate","count":6},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_0ec389e5-2bd"},"title":"Staff AI Engineer","description":"<p>We&#39;re looking for engineers who think holistically, automate relentlessly, and are fluent in the fast-moving world of AI tooling and infrastructure,but grounded in focused engineering principles.</p>\n<p>Our AI Acceleration organization is building high-impact AI-powered applications that deliver real business value at speed. As a Staff AI Engineer, you&#39;ll play a critical role in designing, building and deploying scalable AI-powered applications through proven software engineering completion combined with pragmatic use of modern Data Science and AI capabilities.</p>\n<p>This is a role for top-tier engineers who are excited about applying AI in practical and scalable ways. We&#39;re looking for strong technical leaders who thrive at the intersection of well-adapted software development and modern AI application.</p>\n<p>You should be comfortable working across the full lifecycle of a product,from ideation, architecture and data modelling to deployment, automation and operations,while navigating ambiguity and driving toward execution. Strong systems thinking, ownership mindset, and the ability to ship value fast are crucial.</p>\n<p>You will work closely with engineers, data scientists, product managers, and business stakeholders to define problems, shape solutions, and ensure models perform reliably in the real world.</p>\n<p>If you&#39;re passionate about building AI solutions that go beyond prototypes,solutions that are engineered for scale, reliability, and real-world value,AI Acceleration is the team for you.</p>\n<p><strong>Job Responsibilities</strong></p>\n<ul>\n<li>Design, develop, and maintain production-grade AI applications and services using modern software engineering practices (CI/CD, testing, observability, cloud-native design).</li>\n<li>Define and implement foundational platforms (e.g., conversational bots, AI-powered search, unstructured data processing, GenBI) that are reusable and scalable across the enterprise.</li>\n<li>Lead architectural decisions, bringing standard processes in software development lifecycle, explainable, and responsible AI.</li>\n<li>Lead multi-functional team initiatives,embedded projects with business stakeholders,to rapidly build and deploy AI solutions that tackle high-priority problems.</li>\n<li>Evaluate and integrate existing AI tools, frameworks, and APIs (e.g., LLMs, vector DBs, retrieval-augmented generation) into robust applications.</li>\n<li>Champion automation in workflows,from data ingestion and preprocessing to model integration and deployment. Define their success criterias, metrics and standard operation procedures.</li>\n<li>Partner with data scientists, product managers, and other engineers to ensure end-to-end delivery and reliability of AI products.</li>\n<li>Stay ahead of with emerging AI technologies but prioritize practical application and delivery over experimental research.</li>\n<li>Chip in to the internal knowledge base, tooling libraries, and documentation to scale engineering practices across the organization.</li>\n<li>Mentor other engineers and data scientists and provide technical leadership across projects, helping set the standard for rigor and impact.</li>\n</ul>\n<p><strong>Job Qualifications</strong></p>\n<ul>\n<li>Required:</li>\n<li>7+ years of professional software engineering experience; ability to independently design and ship complex systems in production.</li>\n<li>Strong programming skills in Python (preferred), Java, or similar languages, with experience in developing microservices, APIs, and backend systems.</li>\n<li>Solid understanding of software architecture, cloud infrastructure (AWS, Azure, or GCP), and modern DevOps practices.</li>\n<li>Experience integrating machine learning models into production systems (e.g., LLMs via APIs, fine-tuning, RAG patterns, embeddings, agents and crew of agents etc.).</li>\n<li>Experience with large language models (LLMs), vector-based search, retrieval-augmented generation (RAG), or unstructured data processing.</li>\n<li>Ability to move quickly while maintaining code quality, test coverage, and operational excellence.</li>\n<li>Strong problem-solving skills and a bias for action, with the ability to navigate ambiguity and lead through complexity.</li>\n<li>Strong experience with technical mentorship and cross-team influence.</li>\n<li>Ability to translate complex technical ideas into clear business insights and communicate effectively with cross-functional partners.</li>\n<li>Preferred:</li>\n<li>Familiarity with AI/ML tools such as LangChain, Haystack, Hugging Face, Weaviate, or similar ecosystems.</li>\n<li>Experience using GenAI frameworks such as LlamaIndex, Crew AI, AutoGen, or similar agentic/LLM orchestration toolkits.</li>\n<li>Experience building reusable modeling components or contributing to internal ML platforms.</li>\n<li>Background in working with embedded teams or in forward-deployed environments where rapid iteration and close business collaboration are key.</li>\n<li>Proficiency in Python and common ML/data science libraries (e.g., scikit-learn, pandas, NumPy, PyTorch, TensorFlow).</li>\n<li>Solid knowledge of machine learning fundamentals, including supervised and unsupervised learning, model evaluation, and statistical inference.</li>\n<li>Exposure to working with unstructured data (documents, conversations, images) and transforming it into usable structured formats.</li>\n<li>Experience building chatbots, search systems, or generative AI interfaces.</li>\n<li>Background in working within platform engineering or internal developer tools teams.</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_0ec389e5-2bd","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Bp","sameAs":"https://careers.bp.com","logo":"https://logos.yubhub.co/careers.bp.com.png"},"x-apply-url":"https://careers.bp.com/job-description/RQ109869?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"onsite","x-experience-level":"staff","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Python","Java","Software architecture","Cloud infrastructure","DevOps practices","Machine learning","Large language models","Vector-based search","Retrieval-augmented generation","Unstructured data processing"],"x-skills-preferred":["LangChain","Haystack","Hugging Face","Weaviate","LlamaIndex","Crew AI","AutoGen","scikit-learn","pandas","NumPy","PyTorch","TensorFlow"],"datePosted":"2026-04-25T12:10:32.238Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"India, Pune"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Automotive","skills":"Python, Java, Software architecture, Cloud infrastructure, DevOps practices, Machine learning, Large language models, Vector-based search, Retrieval-augmented generation, Unstructured data processing, LangChain, Haystack, Hugging Face, Weaviate, LlamaIndex, Crew AI, AutoGen, scikit-learn, pandas, NumPy, PyTorch, TensorFlow"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_2b4a4f1f-f36"},"title":"Data Scientist - GenAI - Consultant","description":"<p>Do you want to boost your career and collaborate with expert, talented colleagues to solve and deliver against our clients&#39; most important challenges? We are growing and are looking for people to join our team. You&#39;ll be part of an entrepreneurial, high-growth environment of over 320,000 employees. Our dynamic organization allows you to work across functional business pillars, contributing your ideas, experiences, diverse thinking, and a strong mindset. Are you ready?</p>\n<p>The Role --------</p>\n<p>We are looking for highly skilled Data Scientists to join our team. As a Data Scientist, you’ll design and deliver GenAI solutions (LLM/RAG) and applied ML components, taking prototypes through to production with strong evaluation, observability and governance. You will work closely with cross-functional teams, including data engineers, analysts, and business stakeholders, to turn data into actionable strategies that drive business outcomes.</p>\n<p>Key Responsibilities --------------------</p>\n<ul>\n<li>Design and deliver GenAI solutions including LLM/RAG (retrieval strategy, embeddings, vector stores, prompt flows, grounding) for enterprise use cases.</li>\n<li>Evaluate and improve solution quality using offline/online metrics (quality, latency, cost) and iterate based on feedback.</li>\n<li>Harden solutions for production with observability/monitoring, tracing, guardrails, safety controls, and reliability practices</li>\n<li>Build and integrate model endpoints into products and workflows (APIs/services), partnering with engineering through to deployment.</li>\n<li>Work across cloud platforms (Azure/AWS/GCP) integrating storage, compute, orchestration, and model/runtime components.</li>\n<li>Assess data readiness for modelling/RAG (fitness, quality, access) and define remediation requirements</li>\n<li>Collaborate in cross-functional squads (DS/DE/engineering/product) and contribute to reusable assets and ways of working.</li>\n<li>Communicate clearly with stakeholders on trade-offs, evaluation results, risks, and adoption actions.</li>\n<li>Own end-to-end workstream delivery, lead stakeholder conversations, mentor others. (more senior levels)</li>\n<li>Shape solution direction and quality bar, coach teams, contribute to sales pursuits/bids and accelerators (most senior levels)</li>\n</ul>\n<p>Requirements ------------</p>\n<p><strong>Essential Skills:</strong></p>\n<ul>\n<li>Strong Python/R (pandas/NumPy; ML libs such as scikit-learn; DL frameworks TensorFlow/PyTorch).</li>\n<li>Experience with LLM/RAG toolchains (e.g., LangChain, LlamaIndex, Semantic Kernel) and vector search (e.g., Pinecone, Weaviate, FAISS, Azure AI Search).</li>\n<li>Experience with GenAI platforms (e.g., OpenAI API, Anthropic, Gemini, Llama or equivalents).</li>\n<li>Exposure to big data/distributed computing and pipeline/feature engineering.</li>\n<li>LLM safety &amp; governance (hallucination mitigation, grounded responses, audit trails)</li>\n<li>Degree in a quantitative field</li>\n<li>Right to work in the UK without sponsorship</li>\n</ul>\n<p><strong>Preferred Skills:</strong></p>\n<ul>\n<li>Cloud ML experience (AWS/GCP/Azure).</li>\n<li>Strong SQL; experience with visualisation tools (Tableau/Power BI or Python viz).</li>\n<li>Specialisms: NLP / computer vision / time series.</li>\n<li>NoSQL familiarity.</li>\n<li>Quant / trading analytics engineering practices</li>\n<li>Time-series forecasting (prices, demand, blend outcomes, scheduling effects)</li>\n<li>Optimisation / simulation (planning, blending, logistics constraints)</li>\n<li>Model risk controls (bias/leakage checks, backtesting discipline, monitoring/drift)</li>\n<li>CI/CD, deployment, monitoring; Docker/Kubernetes.</li>\n<li>Experiment design and randomised trials.</li>\n<li>MSc with PhD a plus</li>\n</ul>\n<p>Personal attributes</p>\n<ul>\n<li>Analytical, pragmatic problem-solver; outcome-oriented.</li>\n<li>Self-directed, able to prioritise and juggle multiple workstreams.</li>\n<li>Clear communicator who can simplify complexity.</li>\n<li>Collaborative, curious, continuous learner.</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_2b4a4f1f-f36","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Infosys Consulting - Europe","sameAs":"https://www.infosys.com/","logo":"https://logos.yubhub.co/infosys.com.png"},"x-apply-url":"https://jobs.workable.com/view/3Q492AhHyLQVx6RQtvfQXV/hybrid-data-scientist---genai---consultant-in-london-at-infosys-consulting---europe?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Python","R","pandas","NumPy","scikit-learn","TensorFlow","PyTorch","LangChain","LlamaIndex","Semantic Kernel","Pinecone","Weaviate","FAISS","Azure AI Search","OpenAI API","Anthropic","Gemini","Llama","big data","distributed computing","pipeline","feature engineering","LLM safety","governance","hallucination mitigation","grounded responses","audit trails","degree in a quantitative field","right to work in the UK without sponsorship"],"x-skills-preferred":["cloud ML experience","strong SQL","visualisation tools","NLP","computer vision","time series","NoSQL","quant","trading analytics engineering","time-series forecasting","optimisation","simulation","model risk controls","CI/CD","deployment","monitoring","Docker","Kubernetes","experiment design","randomised trials","MSc with PhD"],"datePosted":"2026-04-24T14:13:18.122Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"London"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, R, pandas, NumPy, scikit-learn, TensorFlow, PyTorch, LangChain, LlamaIndex, Semantic Kernel, Pinecone, Weaviate, FAISS, Azure AI Search, OpenAI API, Anthropic, Gemini, Llama, big data, distributed computing, pipeline, feature engineering, LLM safety, governance, hallucination mitigation, grounded responses, audit trails, degree in a quantitative field, right to work in the UK without sponsorship, cloud ML experience, strong SQL, visualisation tools, NLP, computer vision, time series, NoSQL, quant, trading analytics engineering, time-series forecasting, optimisation, simulation, model risk controls, CI/CD, deployment, monitoring, Docker, Kubernetes, experiment design, randomised trials, MSc with PhD"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_62efca6f-b6f"},"title":"Senior AI Engineer","description":"<p>We&#39;re looking for a Senior AI Engineer who is obsessed with building AI systems that actually work in production: reliable, observable, cost-efficient, and genuinely useful. This is not a research role. You will ship AI-powered features that process real financial data for real businesses.</p>\n<p>LLM &amp; AI Pipeline Engineering - Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</p>\n<p>Develop and operate AI features within Jeeves&#39;s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</p>\n<p>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</p>\n<p>Evaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.</p>\n<p>Establish prompt versioning and evaluation practices to ensure AI outputs remain accurate and consistent as models and data evolve.</p>\n<p>Retrieval &amp; Vector Search - Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</p>\n<p>Build document ingestion and chunking pipelines for Jeeves&#39;s financial data , processing invoices, receipts, policy documents, and transaction records.</p>\n<p>Optimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re-ranking techniques.</p>\n<p>ML Model Serving &amp; Operations - Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</p>\n<p>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</p>\n<p>Implement model performance monitoring and data drift detection to ensure production models remain accurate over time.</p>\n<p>Support model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.</p>\n<p>Backend Integration &amp; Reliability - Integrate AI services cleanly with Jeeves&#39;s backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.</p>\n<p>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</p>\n<p>Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.</p>\n<p>Collaboration &amp; Growth - Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</p>\n<p>Contribute to a culture of quality by writing design docs, reviewing peers&#39; AI system designs, and sharing learnings openly.</p>\n<p>Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_62efca6f-b6f","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Jeeves","sameAs":"https://www.jeeves.com/","logo":"https://logos.yubhub.co/jeeves.com.png"},"x-apply-url":"https://jobs.lever.co/tryjeeves/ded9e04e-f18e-4d4c-ae43-4b7882c6200b?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["LLM","AI","Python","LangChain","LlamaIndex","OpenAI API","Anthropic API","HuggingFace","vector databases","Pinecone","Weaviate","pgvector","semantic search","RAG-based features","document ingestion","chunking pipelines","embedding model selection","chunk strategy","metadata filtering","re-ranking techniques","model serving infrastructure","latency SLOs","input validation","output monitoring","model performance monitoring","data drift detection","clean data pipelines","feature engineering","API contracts","circuit breakers","graceful degradation patterns","structured logging","distributed tracing","latency dashboards","alerting"],"x-skills-preferred":[],"datePosted":"2026-04-17T12:39:23.341Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"India"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"LLM, AI, Python, LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases, Pinecone, Weaviate, pgvector, semantic search, RAG-based features, document ingestion, chunking pipelines, embedding model selection, chunk strategy, metadata filtering, re-ranking techniques, model serving infrastructure, latency SLOs, input validation, output monitoring, model performance monitoring, data drift detection, clean data pipelines, feature engineering, API contracts, circuit breakers, graceful degradation patterns, structured logging, distributed tracing, latency dashboards, alerting"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_e2350d04-53f"},"title":"Senior AI Engineer","description":"<p>We&#39;re looking for a Senior AI Engineer who is obsessed with building AI systems that actually work in production: reliable, observable, cost-efficient, and genuinely useful. This is not a research role. You will ship AI-powered features that process real financial data for real businesses.</p>\n<p>LLM &amp; AI Pipeline Engineering - Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</p>\n<p>Develop and operate AI features within Jeeves&#39;s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</p>\n<p>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</p>\n<p>Evaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.</p>\n<p>Establish prompt versioning and evaluation practices to ensure AI outputs remain accurate and consistent as models and data evolve.</p>\n<p>Retrieval &amp; Vector Search - Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</p>\n<p>Build document ingestion and chunking pipelines for Jeeves&#39;s financial data , processing invoices, receipts, policy documents, and transaction records.</p>\n<p>Optimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re-ranking techniques.</p>\n<p>ML Model Serving &amp; Operations - Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</p>\n<p>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</p>\n<p>Implement model performance monitoring and data drift detection to ensure production models remain accurate over time.</p>\n<p>Support model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.</p>\n<p>Backend Integration &amp; Reliability - Integrate AI services cleanly with Jeeves&#39;s backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.</p>\n<p>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</p>\n<p>Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.</p>\n<p>Collaboration &amp; Growth - Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</p>\n<p>Contribute to a culture of quality by writing design docs, reviewing peers&#39; AI system designs, and sharing learnings openly.</p>\n<p>Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_e2350d04-53f","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Jeeves","sameAs":"https://www.jeeves.com/","logo":"https://logos.yubhub.co/jeeves.com.png"},"x-apply-url":"https://jobs.lever.co/tryjeeves/66241934-7138-4d7d-8b05-a211ec5d6e24?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["LLM","AI","Python","LangChain","LlamaIndex","OpenAI API","Anthropic API","HuggingFace","vector databases","Pinecone","Weaviate","pgvector","PostgreSQL","async patterns","cloud infrastructure","AWS","GCP","Azure","structured logging","distributed tracing","latency dashboards","alerting"],"x-skills-preferred":[],"datePosted":"2026-04-17T12:38:54.694Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Colombia"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"LLM, AI, Python, LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases, Pinecone, Weaviate, pgvector, PostgreSQL, async patterns, cloud infrastructure, AWS, GCP, Azure, structured logging, distributed tracing, latency dashboards, alerting"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_d477874c-cf5"},"title":"Senior AI Engineer","description":"<p>We&#39;re looking for a Senior AI Engineer who is obsessed with building AI systems that actually work in production: reliable, observable, cost-efficient, and genuinely useful. This is not a research role. You will ship AI-powered features that process real financial data for real businesses.</p>\n<p>LLM &amp; AI Pipeline Engineering - Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</p>\n<p>Develop and operate AI features within Jeeves&#39;s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</p>\n<p>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</p>\n<p>Evaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.</p>\n<p>Establish prompt versioning and evaluation practices to ensure AI outputs remain accurate and consistent as models and data evolve.</p>\n<p>Retrieval &amp; Vector Search - Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</p>\n<p>Build document ingestion and chunking pipelines for Jeeves&#39;s financial data , processing invoices, receipts, policy documents, and transaction records.</p>\n<p>Optimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re-ranking techniques.</p>\n<p>ML Model Serving &amp; Operations - Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</p>\n<p>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</p>\n<p>Implement model performance monitoring and data drift detection to ensure production models remain accurate over time.</p>\n<p>Support model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.</p>\n<p>Backend Integration &amp; Reliability - Integrate AI services cleanly with Jeeves&#39;s backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.</p>\n<p>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</p>\n<p>Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.</p>\n<p>Collaboration &amp; Growth - Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</p>\n<p>Contribute to a culture of quality by writing design docs, reviewing peers&#39; AI system designs, and sharing learnings openly.</p>\n<p>Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_d477874c-cf5","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Jeeves","sameAs":"https://www.jeeves.com/","logo":"https://logos.yubhub.co/jeeves.com.png"},"x-apply-url":"https://jobs.lever.co/tryjeeves/639e39d0-b357-4bc2-aff2-968cdedb14b6?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["LLM","AI","Python","Go","Node.js","Pinecone","Weaviate","pgvector","LangChain","LlamaIndex","OpenAI API","Anthropic API","HuggingFace","vector databases","API contracts","circuit breakers","graceful degradation patterns","structured logging","distributed tracing","latency dashboards","alerting"],"x-skills-preferred":[],"datePosted":"2026-04-17T12:38:44.910Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Argentina"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"LLM, AI, Python, Go, Node.js, Pinecone, Weaviate, pgvector, LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases, API contracts, circuit breakers, graceful degradation patterns, structured logging, distributed tracing, latency dashboards, alerting"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_9aa7a5d2-3bd"},"title":"Senior AI Engineer","description":"<p>We&#39;re looking for a Senior AI Engineer who is obsessed with building AI systems that actually work in production: reliable, observable, cost-efficient, and genuinely useful. This is not a research role. You will ship AI-powered features that process real financial data for real businesses.</p>\n<p>LLM &amp; AI Pipeline Engineering</p>\n<ul>\n<li>Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</li>\n<li>Develop and operate AI features within Jeeves&#39;s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</li>\n<li>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</li>\n</ul>\n<p>Retrieval &amp; Vector Search</p>\n<ul>\n<li>Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</li>\n<li>Build document ingestion and chunking pipelines for Jeeves&#39;s financial data , processing invoices, receipts, policy documents, and transaction records.</li>\n</ul>\n<p>ML Model Serving &amp; Operations</p>\n<ul>\n<li>Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</li>\n<li>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</li>\n</ul>\n<p>Backend Integration &amp; Reliability</p>\n<ul>\n<li>Integrate AI services cleanly with Jeeves&#39;s backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.</li>\n<li>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</li>\n</ul>\n<p>Collaboration &amp; Growth</p>\n<ul>\n<li>Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</li>\n<li>Contribute to a culture of quality by writing design docs, reviewing peers&#39; AI system designs, and sharing learnings openly.</li>\n<li>Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_9aa7a5d2-3bd","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Jeeves","sameAs":"https://www.jeeves.com/","logo":"https://logos.yubhub.co/jeeves.com.png"},"x-apply-url":"https://jobs.lever.co/tryjeeves/03f901fc-7a43-4fae-9916-3b287a4bdff6?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Python","LLM","RAG","Pinecone","Weaviate","pgvector","ML model serving","backend engineering","API design","circuit breakers","graceful degradation","Go","Node.js"],"x-skills-preferred":[],"datePosted":"2026-04-17T12:38:17.504Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mexico"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"Python, LLM, RAG, Pinecone, Weaviate, pgvector, ML model serving, backend engineering, API design, circuit breakers, graceful degradation, Go, Node.js"}]}