Senior RL Researcher: Async Systems for Frontier Models

Thinking Machines is seeking a researcher to own the boundary between reinforcement learning algorithms and the underlying systems. The role focuses on high-training-compute, long-horizon RL, with a center of gravity around asynchronous RL and integration with inference constraints. You will co-design the RL recipe and the systems, advance async RL, and run frontier-scale RL end-to-end. Candidates should have strong Python and DL framework experience, and a PhD or equivalent research background