Research Scientist, Robotics & AI

The Role

We are looking for Research Scientists to lead research that makes robots more capable and dexterous. You will develop new learning methods across reinforcement learning, imitation learning, and foundation models, run large-scale training, and take your work from simulation to real robots and into our products.

Responsibilities

• Develop new algorithms and methods for training AI models for enhancing the robot dexterity.
• Conduct cutting edge research across multiple disciplines (Robotics, RL/IL, control, perception, LLM, VLM, etc.).
• Work with large-scale ML systems and large-scale model training/fine-tuning.
• Design and implement state-of-the-art learning-based manipulation/navigation/control algorithms on real robots.
• Work with other teams to develop a diverse set of robust manipulation skills for robots.

Minimum Qualifications

• Ph.D. degree in Robotics, Computer Science/Engineering, Electrical Engineering, Mechanical Engineering, etc., or equivalent research experience.
• Passionate about working with robots and building robot products.
• Excellent analytical, problem-solving, and communication skills.
• At least 3 years of experience conducting independent research.
• Deep understanding of the SOTA robot learning techniques (reinforcement learning, imitation learning, etc.)
• A track record of research excellence with your work published in top conferences and journals such as Science Robotics, IJRR, RSS, CoRL, ICRA, NeurIPS, ICML, ICLR, CVPR, etc.
• Proficient with Python.
• Proficient with deep learning libraries such as PyTorch/TensorFlow/Jax.
• Experience with real robot experiments.
• Experienced with robot simulators such as Isaac Gym/ Isaac Sim/ SAPIEN/ MuJoCo/Drake, etc.