Researcher, Robot Learning

The role

You will own generalist policy research for the Asimov humanoid robot platform. You will train vision-language-action models and build imitation learning pipelines to turn data into general-purpose behavior.

What you will do

• Own Asimov's generalist policy research end to end
• Train and post-train vision-language-action models and other generalist policies
• Build imitation learning pipelines on teleoperation and demonstration data
• Design the self-improvement loop including autonomous data collection and success detection
• Combine learning from demonstrations, reinforcement learning, and simulation
• Define evaluations for policy performance on real hardware
• Partner with World Models, Locomotion and Manipulation, and Platform teams
• Publish, open-source, and share research with the community

Required qualifications

• Deep hands-on experience training learning-based robot policies through imitation learning, reinforcement learning, or both
• Experience taking a learned policy from research code to a physical robot
• Fluent in Python and PyTorch
• Comfortable training at scale on multi-GPU clusters
• Knowledge of how dataset composition, quality, and diversity shape policy performance
• PhD or equivalent research experience in robot learning, ML, or a related field, or a portfolio that speaks for itself
• Communicate clearly through papers, blogs, talks, or well-documented code
• Use AI as a real collaborator in research

Nice to have

• Experience with VLA models or robot foundation models such as OpenVLA, Octo, or π0
• Work with diffusion policies, flow matching, or action chunking
• Experience with autonomous data collection, reward learning, or continual learning on real robots
• Time on humanoids or other high-DoF, whole-body platforms
• Familiarity with large-scale simulation in Isaac Lab, MuJoCo, or mjlab
• Published work at CoRL, RSS, ICRA, NeurIPS, or similar venues
• Contributions to open-source robot learning libraries such as LeRobot

About the company

Menlo Research is an Applied R&D lab building Asimov, an open-source humanoid robot platform, and the full software stack that powers it.