Full‑Stack Software Engineer in Reinforcement Learning at Anthropic. Responsible for building platforms, tools, and interfaces that enable environment creation, data collection, and training observability. Own product surfaces end‑to‑end from backend services and APIs to web UIs used by researchers, vendors, and data labelers.
Full-Stack Software Engineer, Reinforcement Learning at Anthropic
On-site - San Francisco, CA | New York City, NY
More jobs at AnthropicRequirements
Skills
- Strong software engineering fundamentals and full‑stack experience from database schema to frontend
- Proficiency in Python and a modern web stack such as React or TypeScript
- Track record of shipping systems that solve hard problems
- High agency and ability to drive work without waiting for tickets
- UX‑centric mindset for building intuitive interfaces for technical and non‑technical users
- Clear communication with researchers, operations teams, and engineers
- Interest in Anthropic’s mission to build safe, beneficial AI
- Experience building data collection, labeling, or annotation platforms at scale
- Background in multi‑tenant platforms with role‑based access, audit trails, and vendor management
- Experience with cloud infrastructure (GCP or AWS), Docker, and CI/CD pipelines
- Familiarity with LLM training, fine‑tuning, or evaluation workflows
- Experience with async Python (Trio, asyncio) or high‑throughput API design
- Background in dashboards, monitoring, or observability tooling
- Experience integrating with external vendors or partners on technical integrations
Responsibilities
- Build and extend web platforms for RL environment creation, management, and quality review
- Develop vendor‑facing interfaces and tooling to enable partners to create, submit, and iterate on training environments
- Design and implement platforms for human data collection at scale, including labeling workflows and quality assurance systems
- Build evaluation dashboards and observability UIs for real‑time insights into environment quality and training run health
- Create backend services and APIs connecting authoring tools, data collection systems, and RL training infrastructure
- Build scalable code data generation pipelines to produce diverse programming tasks with robust reward signals
- Develop onboarding automation and documentation tooling for new vendors and internal users
- Partner closely with RL researchers, data operations, and vendor management to translate ambiguous requirements into well‑scoped products
Technologies
PythonReactTypeScriptDockerGCPAWSasync PythonCI/CD pipelinesLLM training toolsObservability dashboards
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.