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.
You will design training procedures, build evals for failure modes, run experiments, and publish the results.
Training infrastructure.
Environment selection.
Algorithms and capability retention.
Evals and stability at long horizons.
#J-18808-Ljbffr
The Member of Technical Staff, RL position in the IT & Technology field is open for applications.
We are seeking a motivated Member of Technical Staff, RL to join Pdoom in München, Bayern, Germany.
Consider building your career as a Member of Technical Staff, RL at Pdoom.
We have an opening for a Member of Technical Staff, RL in München, Bayern, Germany within IT & Technology.
This role, Member of Technical Staff, RL at Pdoom, could be your next move.