Full-Stack Software Engineer, Reinforcement Learning

About this role

Join Anthropic's Reinforcement Learning team as a Full-Stack Software Engineer building platforms that power environment creation, data collection, and training for Claude. You'll own products end-to-end—from backend APIs to web interfaces used by researchers and thousands of data labelers—in a fast-moving environment where iteration happens in hours, not months.

What you'll do

• Build web platforms for RL environment creation, management, versioning, and quality review
• Develop vendor-facing interfaces for external partners to create and iterate on training environments
• Design human data collection platforms at scale with labeling workflows and quality assurance systems
• Create evaluation dashboards and observability UIs for training run health and environment quality
• Implement backend services and APIs connecting environment tools, data collection, and RL infrastructure
• Build scalable code data generation pipelines producing diverse programming tasks with reward signals

What they're looking for

• Full-stack software engineering (database to frontend)
• Python
• React, TypeScript, or modern web frameworks
• System design for scalable platforms
• UX design and user interface development
• Cross-functional communication with researchers and operations teams
• High agency and problem-solving in ambiguous situations
• Data collection and labeling platform experience (preferred)