As a Full-Stack Software Engineer in RL, you'll build the platforms, tools, and interfaces that power environment creation, data collection, and training observability. The quality of Claude's next generation depends on the quality of the data we train it on , and the systems you build are what make that data possible. You'll own product surfaces end-to-end , from backend services and APIs to the web UIs that researchers, external vendors, and thousands of data labelers use every day.\\n\\nYou don't need a background in ML research. What matters is that you can take an ambiguous, high-stakes problem and ship a polished, reliable product against it, fast. This team moves very quickly. Claude writes a lot of the code we commit, which means the bottleneck isn't typing , it's judgment, taste, and the ability to react to what researchers need next.\\n\\nYou'll iterate on data collection strategies to distill the knowledge of thousands of human experts around the world into our models, and you'll do it in a loop that closes in hours and days, not quarters or months.\\n\\nAnthropic's Reinforcement Learning organization leads the research and development that trains Claude to be capable, reliable, and safe. We've contributed to every Claude model, with significant impact on the autonomy and coding capabilities of our most advanced models.\\n\\nOur work spans teaching models to use computers effectively, advancing code generation through RL, pioneering fundamental RL research for large language models, and building the scalable training methodologies behind our frontier production models.\\n\\nThe RL org is organized around four goals: solving the science of long-horizon tasks and continual learning, scaling RL data and environments to be comprehensive and diverse, automating software engineering end-to-end, and training the frontier production model.\\n\\nOur engineering teams build the environments, evaluation systems, data pipelines, and tooling that make all of this possible , from realistic agentic training environments and scalable code data generation to human data collection platforms and production training operations.\\n\\n### Responsibilities\\n\\n Build and extend web platforms for RL environment creation, management, and quality review , including environment configuration, versioning, and validation workflows\\n Develop vendor-facing interfaces and tooling that let external partners create, submit, and iterate on training environments with minimal friction\\n Design and implement platforms for human data collection at scale, including labeling workflows, quality assurance systems, and feedback mechanisms that surface reward signal integrity issues early\\n Build evaluation dashboards and observability UIs that give researchers real-time insight into environment quality, training run health, and reward hacking\\n Create backend services and APIs that connect environment authoring tools, data collection systems, and RL training infrastructure\\n Build and expand scalable code data generation pipelines, producing diverse programming tasks with robust reward signals across languages and difficulty levels\\n Develop onboarding automation and documentation tooling so new vendors and internal users ramp up in hours, not weeks\\n Partner closely with RL researchers, data operations, and vendor management to translate ambiguous requirements into well-scoped, well-designed products\\n\\n### Requirements\\n\\n Strong software engineering fundamentals and real full-stack range , you're comfortable owning a surface from database schema to frontend\\n Proficient in Python and a modern web stack (React, TypeScript, or similar)\\n Track record of shipping systems that solved a hard problem, not just shipped on time , e.g. you built the thing that made your team 10x faster, or the internal tool nobody thought was possible\\n Operate with high agency: you identify what needs to be done and drive it forward without waiting for a ticket\\n Found yourself wondering "why isn't this moving faster?" in previous roles , and then have done something about it\\n Care about UX and can build interfaces that are intuitive for both technical researchers and non-technical labelers\\n Communicate clearly with researchers, operations teams, and engineers, and can turn vague asks into well-scoped work\\n Thrive in a fast-moving environment where priorities shift, Claude is your pair programmer, and the next problem is often one nobody has solved before\\n Care about Anthropic's mission to build safe, beneficial AI and want your work to contribute directly to it\\n\\n### Nice to Have\\n\\n Built data collection, labeling, or annotation platforms , ideally ones that had to scale across many vendors or many task types\\n Background building multi-tenant platforms with role-based access, audit trails, and vendor management workflows\\n Experience with cloud infrastructure (GCP or AWS), Docker, and CI/CD pipelines\\n Familiarity with LLM training, fine-tuning, or evaluation workflows\\n Experience with async Python (Trio, asyncio) or high-throughput API design\\n Background in dashboards, monitoring, or observability tooling\\n Experience working directly with external vendors or partners on technical integrations\\n A background that isn't a straight line , e.g. math or physics into SWE, competitive programming, research into engineering, or a side project that outgrew its scope\\n\\n### Representative Projects\\n\\n Building a unified platform for human data collection that integrates labeling workflows, vendor management, and QA for complex agentic tasks\\n Developing vendor onboarding automation that handles Docker registry access, API token management, and environment validation\\n Creating evaluation and observability dashboards that catch reward hacks, measure environment difficulty, and give real-time feedback during production training\\n Building environment quality review workflows that let researchers browse, grade, and provide feedback on training environments\\n Developing automated environment quality pipelines that validate correctness and difficulty calibration before environments hit production training\\n* Building internal tools for browsing and analyzing training run results, environment statistics, and data collection progress
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_b2637f59-e14","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://www.anthropic.com/","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/5186067008","x-work-arrangement":"hybrid","x-experience-level":"staff","x-job-type":"full-time","x-salary-range":"$300,000-$405,000 USD","x-skills-required":["Python","Modern web stack","React","TypeScript","Strong software engineering fundamentals","Full-stack range","Database schema","Frontend","Cloud infrastructure","Docker","CI/CD pipelines","LLM training","Fine-tuning","Evaluation workflows","Async Python","High-throughput API design","Dashboards","Monitoring","Observability tooling"],"x-skills-preferred":["Data collection","Labeling","Annotation platforms","Multi-tenant platforms","Role-based access","Audit trails","Vendor management workflows"],"datePosted":"2026-04-18T15:54:27.784Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA | New York City, NY"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Modern web stack, React, TypeScript, Strong software engineering fundamentals, Full-stack range, Database schema, Frontend, Cloud infrastructure, Docker, CI/CD pipelines, LLM training, Fine-tuning, Evaluation workflows, Async Python, High-throughput API design, Dashboards, Monitoring, Observability tooling, Data collection, Labeling, Annotation platforms, Multi-tenant platforms, Role-based access, Audit trails, Vendor management workflows","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":300000,"maxValue":405000,"unitText":"YEAR"}}},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_4a77b359-de1"},"title":"Principal Engineer, Web Platform – Team Web","description":"As our Principal Engineer, you will shape the technical direction and architectural evolution of our web platform and systems. You'll act as the technical leader across our marketing and growth web surfaces, partnering with marketing, analytics, design, data science, and engineering teams to ensure our web stack is modern, performant, measurable, and delightful to build on.
\nYou'll operate with a high degree of autonomy and will be accountable for setting the long-term technical strategy for the team and executing against it.
\nAs a senior technical leader, you will:
\nOwn and evolve the architecture of Intercom's web stack. Define the long-term technical strategy for the web team, focusing on scalability, performance, developer productivity, observability, and system reliability. Collaborate closely with marketing, design, analytics, and data science stakeholders to ensure the platform supports their goals with accuracy, performance, and agility. Lead and influence the design and implementation of MarTech systems for event tracking, attribution, funnel reporting, A/B testing infrastructure, and more. Partner with engineers across web, infrastructure, and data to create a high-quality, cohesive technical ecosystem. Mentor and elevate engineers across the team and organisation , providing guidance on architecture, data modeling, system design, and engineering best practices. Set the standard for technical excellence in reliability, maintainability, code quality, and operational readiness. Provide technical leadership and insight to Engineering Managers, Product Managers, and executive stakeholders , communicating risks, trade-offs, and opportunities clearly. Contribute hands-on to the codebase , leading by example and helping unblock and accelerate key projects.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_4a77b359-de1","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Intercom","sameAs":"https://www.intercom.com/","logo":"https://logos.yubhub.co/intercom.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/intercom/jobs/7515664","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["12+ years of software engineering experience","Experience in a high-scale growth-focused web environment","A track record of technical leadership and influencing technical direction across multiple teams or departments","Deep familiarity with modern web stacks and infrastructure","Strong understanding of data infrastructure, including event instrumentation, and analytics tooling","Comfortable working in and supporting full-stack codebases","Experience operating in continuous delivery environments with an emphasis on incremental, high-quality shipping","Exceptional communication skills and a history of collaborating with cross-functional teams"],"x-skills-preferred":[],"datePosted":"2026-04-18T15:54:25.996Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Dublin, Ireland"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"12+ years of software engineering experience, Experience in a high-scale growth-focused web environment, A track record of technical leadership and influencing technical direction across multiple teams or departments, Deep familiarity with modern web stacks and infrastructure, Strong understanding of data infrastructure, including event instrumentation, and analytics tooling, Comfortable working in and supporting full-stack codebases, Experience operating in continuous delivery environments with an emphasis on incremental, high-quality shipping, Exceptional communication skills and a history of collaborating with cross-functional teams"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_76fd624c-e23"},"title":"Full-Stack Software Engineer, Reinforcement Learning","description":"As a Full-Stack Software Engineer in RL, you'll build the platforms, tools, and interfaces that power environment creation, data collection, and training observability. The quality of Claude's next generation depends on the quality of the data we train it on , and the systems you build are what make that data possible. You'll own product surfaces end-to-end , from backend services and APIs to the web UIs that researchers, external vendors, and thousands of data labelers use every day. You don't need a background in ML research. What matters is that you can take an ambiguous, high-stakes problem and ship a polished, reliable product against it, fast.
\nThis team moves very quickly. Claude writes a lot of the code we commit, which means the bottleneck isn't typing , it's judgment, taste, and the ability to react to what researchers need next. You'll iterate on data collection strategies to distill the knowledge of thousands of human experts around the world into our models, and you'll do it in a loop that closes in hours and days, not quarters or months.
\nOur work spans teaching models to use computers effectively, advancing code generation through RL, pioneering fundamental RL research for large language models, and building the scalable training methodologies behind our frontier production models. The RL org is organized around four goals: solving the science of long-horizon tasks and continual learning, scaling RL data and environments to be comprehensive and diverse, automating software engineering end-to-end, and training the frontier production model.
\nOur engineering teams build the environments, evaluation systems, data pipelines, and tooling that make all of this possible , from realistic agentic training environments and scalable code data generation to human data collection platforms and production training operations.
\nResponsibilities:
\nYou May Be a Good Fit If You:
\nStrong Candidates May Also Have:
\nRepresentative Projects:
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_76fd624c-e23","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://www.anthropic.com/","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/5186067008","x-work-arrangement":"hybrid","x-experience-level":"staff","x-job-type":"full-time","x-salary-range":"$300,000-$405,000 USD","x-skills-required":["Python","Modern web stack","React","TypeScript","Cloud infrastructure","Docker","CI/CD pipelines","LLM training","Fine-tuning","Evaluation workflows","Async Python","High-throughput API design","Dashboards","Monitoring","Observability tooling"],"x-skills-preferred":["Data collection","Labeling","Annotation","Multi-tenant platforms","Role-based access","Audit trails","Vendor management workflows"],"datePosted":"2026-04-18T15:39:16.596Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA | New York City, NY"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Modern web stack, React, TypeScript, Cloud infrastructure, Docker, CI/CD pipelines, LLM training, Fine-tuning, Evaluation workflows, Async Python, High-throughput API design, Dashboards, Monitoring, Observability tooling, Data collection, Labeling, Annotation, Multi-tenant platforms, Role-based access, Audit trails, Vendor management workflows","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":300000,"maxValue":405000,"unitText":"YEAR"}}}]}