Member of Technical Staff - Senior Software Engineer

Build high-quality reinforcement learning (RL) environments and platform tooling used to train, evaluate, and improve AI agents. Own complex agent environments end-to-end—from frontend to backend—working with Applied Researchers to translate environment designs, task specs, and verifier requirements into robust software. Help frontier labs stress-test the next generation of AI agents, while developing reusable patterns, libraries, and shared infrastructure for running and benchmarking environments across heterogeneous targets.