Key Responsibilities:
Design, implement, test, and deploy manipulation algorithms for humanoid robots with high degree of freedom, highly dexterous hands, including grasping, picking and placing, bimanual manipulation, visual and tactile servoing, and assembly
Train deep learning models for manipulation that are robust to uncertainty, sensor noise, and partial information
Collaborate with other team members to develop toward a full autonomy stack
Define performance metrics, test learned policies, and evaluate their effectiveness in real-world scenarios.
Requirements:
Bachelor's or Master's, PhD's degree in computer science, AI, Mechatronics, Control Engineering - Automation, or a related field
Proficiency in writing production-quality code using PyTorch/Tensorflow/JAX.
Familiarity with online and offline RL algorithms, such as PPO and SAC.
Familiarity with simulation technologies (e.g., IsaacGym, IsaacLab, Mujoco)
Experience in tuning hyperparameters, reward engineering, and optimizing RL training processes.
Understand both traditional and machine learning approaches to robot manipulation, and the tradeoffs between various techniques
Understanding of the latestest development and framework in RL for manipulation
Preferred Qualifications:
Hands-on experience with manipulation tasks and project
Experience with deploying real world robot manipulation solutions
Publication in related field