Full-Stack Software Engineer, Reinforcement Learning

Anthropic is a public benefit corporation headquartered in San Francisco, building reliable, interpretable, and steerable AI systems. The Reinforcement Learning organization leads the research and development that trains Claude, spanning teaching models to use computers, advancing code generation through RL, and building scalable training methodologies.

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 — owning product surfaces end-to-end from backend services and APIs to the web UIs used by researchers, external vendors, and data labelers.

• Build and extend web platforms for RL environment creation, management, and quality review, including configuration, versioning, and validation workflows.
• Develop vendor-facing interfaces and tooling that let external partners create, submit, and iterate on training environments.
• Design and implement platforms for human data collection at scale, including labeling workflows, quality assurance systems, and feedback mechanisms.
• Build evaluation dashboards and observability UIs giving researchers real-time insight into environment quality, training run health, and reward hacking.
• Create backend services and APIs connecting environment authoring tools, data collection systems, and RL training infrastructure.
• Build and expand scalable code data generation pipelines producing diverse programming tasks with robust reward signals.
• Develop onboarding automation and documentation tooling so new vendors and internal users ramp up quickly.

• Strong software engineering fundamentals and full-stack range — comfortable owning a surface from database schema to frontend.
• Proficiency in Python and a modern web stack (React, TypeScript, or similar).
• Track record of shipping systems that solved hard problems; high agency; care about UX; clear communication with researchers, operations teams, and engineers.
• Strong candidates may also have built data collection, labeling, or annotation platforms; multi-tenant platforms with role-based access and audit trails; cloud infrastructure (GCP or AWS), Docker, and CI/CD pipelines; LLM training, fine-tuning, or evaluation workflows; async Python (Trio, asyncio) or high-throughput API design; or dashboards, monitoring, and observability tooling.

Annual salary: $300,000—$405,000 USD.

Apply via the Greenhouse job posting. Anthropic sponsors visas and makes every reasonable effort to obtain them for offered candidates. Minimum education: Bachelor's degree or an equivalent combination of education, training, and/or experience.