Researcher, Manipulation

Highlights

• Give open-source humanoid Asimov hands that can do real physical work.
• Drive grasping and dexterous skills from walking to flipping and beyond.
• Ship whole-body manipulation skills to real robots in the open.

Ideal candidate

Hands-on robotics researcher who lives for getting manipulation onto real hardware and iterating from real failures. You think in whole-body coordination, ship fast, and want open work that others build on.

Requirements

• Deep hands-on experience with reinforcement learning or learning-based methods for manipulation, grasping, or dexterous control
• Track record of getting manipulation policies onto real robots, not only papers or simulators
• Strong command of physics simulator such as MuJoCo or Isaac, including contact modeling, reward shaping, and domain randomization
• Fluency in Python and modern RL tooling, and comfort in ROS2-based control stack
• Bias for shipping and iterating quickly on real hardware
• Clear thinking about why contact-rich tasks fail and how to close the gap