Researcher, Robot Learning

What you'll do

• Own generalist policy research from datasets and hypotheses through training and deployment on physical robots.
• Build imitation-learning and self-improvement pipelines, combining demonstrations, reinforcement learning, and simulation.
• Evaluate policies on real hardware and collaborate across teams to integrate and share research.

What they ask for

• Hands-on experience training learning-based robot policies using imitation learning, reinforcement learning, or both.
• Experience taking a learned policy from research code to a physical robot.
• Fluency in Python and PyTorch, and comfort training at scale on multi-GPU clusters.
• PhD or equivalent research experience in robot learning, ML, or a related field, or a portfolio that speaks for itself.

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.

Tools

Python, PyTorch, OpenVLA, Octo, π0, Isaac Lab, MuJoCo, mjlab

AI focus

Train and post-train vision-language-action models and generalist policies; use AI as a research collaborator.