Member of Technical Staff, RL.

We use RL on computer-use tasks to train models for long-horizon work. The interface is streaming visual observation and low-level actions. Rewards come from task completion or rubric-based generative reward models.

This role owns the RL stack: training infrastructure, environment selection, algorithms, capability retention, evals, and stability at long horizons.

You will design training procedures, build evals for failure modes, run experiments, and publish the results.