Senior Software Engineer - Agentic RL Environments (Remote)
Summary
Build agentic reinforcement-learning environments and benchmarks to evaluate cutting-edge AI coding models, writing tests and success criteria to separate high-quality outputs from failures.
Surge AI is seeking a Senior Software Engineer to build agentic coding RL environments and benchmarks for evaluating frontier models. This contract role offers fully remote work with a compensation range of $100-150+ per hour, depending on experience.
Ideal candidates have production-system experience and strong engineering judgment across modern stacks. You will design tasks, review model outputs, and write tests and success criteria to distinguish high-quality work from failures.