About the Role
Join an early-stage AI company as a Coding RL Engineer, working with the reinforcement learning team to build coding environments and tasks for training and evaluating advanced models. You will turn real-world software engineering work into reproducible benchmarks that help improve coding AI.
What You'll Do
Convert licensed production codebases into reproducible, containerized coding environments.
Use issues, pull requests, commit histories, and incident records to create tasks covering bug fixes, features, refactors, testing, and multi-file agent work.
Build and improve verifiers with hidden tests, rubric-based or model-based grading, and safeguards against reward hacking and answer leakage.
Run model rollouts, review traces, and repair or remove tasks that are broken, ambiguous, too easy, or exploitable.
Contribute tasks and analysis to coding benchmarks and build tools that speed up task creation and validation.
Work with research teams to calibrate task difficulty and benchmark coverage.
What We're Looking For
At least 2 years of professional software engineering experience delivering software systems.
Very strong Python skills and fluency in another language such as TypeScript, Go, Java, or Rust.
Hands-on Docker experience and familiarity with reproducible build and test environments.
Experience navigating unfamiliar, complex codebases and getting them building, running, and tested.
Working knowledge of coding model training and evaluation, including SWE-bench-style tasks, code evaluations, RLVR, and agent harnesses.
Experience creating coding tasks from real engineering work and hardening verifiers against flaky tests, unclear requirements, and leaked solutions.
Relevant experience with frontier AI labs, evaluation teams, RL environments, coding agents, or large enterprise and legacy codebases is helpful.
Location
Remote within the United States or in person in San Francisco, California.