<p>Tesla is building robust embodied intelligence through humanoid robots. You will work on cutting-edge policy learning algorithms that allow the robot to walk, dance, balance, and recover from disturbances in real-world settings. Most importantly, the motion policies that you deploy will be repeatedly shipped and utilized by thousands of humanoid robots in real-world applications.</p> <ul> <li> <p>Develop end-to-end reinforcement-learning policies for whole-body movements</p> </li><li> <p>Design observations, actions, and rewards based on first principles and deep physics understanding</p> </li><li> <p>Develop techniques to improve sim2real transfer, including classical modeling techniques</p> </li><li> <p>Evaluate policies both in simulation and on hardware</p> </li><li> <p>Ship production-quality policies to a fleet of bots</p> </li><li> <p>Experience writing production-quality python (including numpy and pytorch)</p> </li><li> <p>Solid understanding of robotics fundamentals, including geometry, linear algebra, kinematics, dynamics, probability, and statistics</p> </li><li> <p>Familiarity with Machine learning and Reinforcement Learning fundamentals OR strong background in optimization-based planning and control</p> </li><li> <p>Experience working with robotic systems, ideally on legged robotic systems with high degrees of freedom</p> </li><li> <p>Experience with sim2real techniques OR deep understanding of physics fundamentals</p> </li><li> <p>Experience implementing control strategies including impedance control, adaptive control, force control, MPC on hardware preferred</p> </li></ul>