Anthropic
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)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Anthropic
Anthropic builds Claude, an AI assistant, and is hiring for engineering roles across infrastructure, data systems, and security that support both AI research operations and the company's internal technology needs. The company seeks infrastructure engineers, systems integrators, data scientists, and security specialists to build production-scale systems for training data pipelines, financial operations, developer productivity measurement, research infrastructure, and server firmware security.
- Website
- anthropic.com
Likely interview questions
- Walk us through a time you built a full-stack system (backend to frontend) that solved a hard problem and made your team significantly faster. What was the bottleneck, and how did you approach solving it?
- Describe your experience with Python and modern web frameworks (React, TypeScript, etc.). What's a complex feature you've built end-to-end, and how did you handle the technical decisions?