Menlo Research
Researcher, Locomotion
Singapore +1 · Hybrid · Full-time · Posted Sep 4, 2026
- Location
- Singapore
Palo Alto
About the job
Develop and deploy robust reinforcement-learning locomotion policies for Menlo’s Asimov humanoid robots, taking them from simulation to real hardware.
What you'll do
- Design, train, and ship bipedal and whole-body locomotion policies, including balance, gait, and recovery behaviors.
- Own and improve the sim2real pipeline; use robot telemetry and hardware testing to refine policies.
- Develop reward design, domain randomization, and MuJoCo training environments; share findings through open-source work and write-ups.
What they ask for
- Hands-on experience with reinforcement learning for continuous control, legged locomotion, or whole-body control.
- Track record of deploying learned policies on real robots.
- Strong command of a physics simulator such as MuJoCo, Isaac, or similar, including reward shaping and domain randomization.
- Fluency in Python and modern RL tooling, and comfort with a ROS2-based control stack.
Nice to have
- Published work in locomotion, legged robotics, or sim2real transfer.
- Experience with model predictive control or classical locomotion methods alongside learning-based approaches.
Tools
MuJoCo, Isaac, Python, ROS2
AI focus
Develop reinforcement-learning locomotion policies for humanoid robots and deploy them on real hardware.
Model-written summary · the original posting is authoritative