Reinforcement Learning Engineer - Locomanipulation

Humanoid seeks a skilled Reinforcement Learning Engineer focused on developing advanced locomotion capabilities. This critical role involves designing and implementing robust RL algorithms to optimize gaits, balance, and overall mobility for our next generation of bipedal robots. Key responsibilities include building high-fidelity simulation environments (e.g., MuJoCo, Isaac Gym), training agents on complex dynamic tasks, and refining controllers for real-world deployment. The ideal candidate possesses deep expertise in continuous control theory and state-of-the-art RL methods like SAC or PPO. You will collaborate closely with Controls Engineers to translate theoretical advancements into functional hardware behaviors, ensuring the robots can operate safely and efficiently across diverse environments. Qualifications include a strong background in machine learning, experience with Python/C++, and practical knowledge of robotics simulation pipelines.

(تازہ ترین نوکریاں، سلیبس اور ٹیسٹ کی تیاری کی مکمل معلومات)