Senior Software Engineer: Agentic RL Environments (Remote)
Summary
Build and evaluate reinforcement-learning environments that simulate real software-engineering tasks to test AI coding agents.
Surge AI is seeking a Senior Software Engineer (Agentic Coding RL Environments) to build coding RL environments and benchmarks that test how agents perform on realistic software engineering tasks. The role is contract, fully remote, with compensation ranging by experience. You will design tasks from real engineering work, review model outputs to surface failures, and write tests, rubrics, and success criteria that separate good work from slop. J-18808-Ljbffr