Researcher, Robot Learning

Menlo • Palo Alto, CA

12h

About The Position

Menlo Research is an applied R&D lab building Asimov, an open-source humanoid robot platform and its full software stack. The company aims to make humanoid labor economically viable by developing hardware architecture, locomotion, autonomy, simulation, and infrastructure.

As a researcher on the Brain team, you will develop learning systems that enable Asimov to acquire skills and improve through experience. You will own research into generalist policies, training data, and self-improvement loops, taking ideas from hypotheses and datasets through deployment on physical robots. The work includes training on real robot data, shipping to hardware, and open-sourcing work where possible.

The role collaborates with World Models, Locomotion, Manipulation, and Platform teams so research becomes part of the product stack and supports agents using Asimov through its SDK. Menlo emphasizes short research cycles, real-hardware deployment, and sharing work with the open-source community.

Requirements

• 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 and addressing deployment challenges.
• Fluency in Python and PyTorch.
• Comfort training at scale on multi-GPU clusters.
• Ability to reason about how dataset composition, quality, and diversity shape policy capabilities.
• A PhD or equivalent research experience in robot learning, machine learning, or a related field, or a portfolio that demonstrates relevant ability.
• Clear communication through papers, blogs, talks, or well-documented code.
• Use of AI as a real collaborator in research.

Nice To Haves

• Experience with vision-language-action models or robot foundation models such as OpenVLA, Octo, or π0.
• Experience with diffusion policies, flow matching, or action chunking.
• Experience with autonomous data collection, reward learning, or continual learning on real robots.
• Experience with humanoids or other high-degree-of-freedom, 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.

Responsibilities

• Own Asimov’s generalist policy research end to end, from hypothesis and dataset through to a trained policy running on the physical robot.
• Train and post-train vision-language-action models and other generalist policies that follow instructions and transfer across tasks and environments.
• Build imitation learning pipelines using teleoperation and demonstration data, and determine which data improves performance.
• Design a self-improvement loop covering autonomous data collection, success detection, and learning from deployment.
• Combine learning from demonstrations, reinforcement learning, and simulation to address the sim-to-real gap at scale.
• Define evaluations that measure whether policies improve on real hardware, not only on benchmarks.
• Partner with World Models, Locomotion and Manipulation, and Platform teams to integrate research into the shipping stack.
• Publish, open-source, and share findings with the community building on Asimov.

What This Job Offers

• Job Type: Full-time
• Education Level: Ph.D. or professional degree