Role OverviewThe Software Engineer – Dexterous Manipulation will implement, tune, and deploy reinforcement learning and related learning-based control for high-DOF, multi-fingered robotic hands. You will work across simulation, hardware, and systems teams to get complex manipulation tasks working robustly on real robots.
What You Will Do
Implement and tune control algorithms for multi-fingered hands, develop and maintain manipulation software, translate state-of-the-art methods into production-grade code, build and refine sim-to-real pipelines, and deploy and debug manipulation capabilities on physical robots.
Why It Might Be a Fit
You will collaborate with hardware and systems engineers, feed back on hand performance and sensor/actuator requirements, and uphold code quality through rigorous testing, documentation, and peer review.
Requirements
- Dexterous manipulation experience: multi-fingered grasping, in-hand manipulation, and high-DOF hand control
- Reinforcement learning for robotic control—reward design, training, and debugging—ideally applied to dexterous manipulation
- Strong Python and working C++ for real-time robotic software
- Hands-on experience training and validating policies in a physics simulator (IsaacSim, MuJoCo, or Drake)
- Robotics fundamentals: kinematics, dynamics, and Jacobian-based control
- A track record of getting algorithms working on physical hardware, not simulation alone
]]>