Full-Stack Software Engineer, Reinforcement Learning

Overview

Full-Stack Software Engineer (RL) building platforms, tools, and interfaces for RL environment creation, data collection, and training observability.

What you'll do

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

What you'll need

• Strong software engineering fundamentals and full-stack range from database schema to frontend.
• Proficiency in Python and a modern web stack (React, TypeScript, or similar).
• Experience shipping systems that solved hard problems (not just on-time delivery).
• High agency to drive work forward without waiting for tickets.
• Ability to care about UX and build intuitive interfaces for technical researchers and non-technical labelers.
• Clear communication to turn vague requirements into well-scoped work.

Details

• Hybrid work policy: expected to be in an office at least 25% of the time.
• Visa sponsorship is available; not guaranteed for every role/candidate.