Research Engineer (Post-Training ​/ RL) Munich or Zurich

The next ten years of AI will not be won in software. They will be won in the physical world. In factories, hospitals, kitchens, fields, and homes. The companies that own that data will own the century.

microagi is building it. We are the data layer for physical AI.

This role is one half of a pair. You will work day to day with one of our researchers on post-training for robot policies. Reinforcement learning, simulation, and the work of getting something that behaves in simulation to behave on a real machine. Most days you will be at the same screen, arguing about the next experiment.

• Post-train robot policies with reinforcement learning and related methods.
• Build and tune simulation environments, then close the gap to the real robot.
• Run experiments daily. Keep what holds up and throw away the rest.
• Build the reward, evaluation, and logging infrastructure the experiments depend on.
• Take a policy from simulation onto hardware and make it survive contact with the physical world.
• Pair-program most of the day. This seat only works if you like thinking out loud.

• Real reinforcement learning experience. You have trained policies that worked, and you know why the others did not.
• Experience with robot simulation and sim-to-real transfer.
• Strong Python and PyTorch or JAX.
• You come from a serious robotics or AI group, in industry or research.
• Comfortable pair-programming for hours at a stretch.
• High agency - you don't wait to be told what to do.

• Isaac Sim, Mu Jo Co , or Mani Skill.
• Vision-language-action models or diffusion policies.