AI Robotics Researcher Intern (Dexterous Manipulation)

About the role#

NIO is seeking an AI Robotics Research Intern to work on embodied AI and dexterous manipulation. This role focuses on utilizing large-scale foundation models and human data-based learning to develop physical world intelligence for robots. You will work on harvesting human-object interaction data to bridge the gap between human dexterity and machine execution, with the goal of deploying policies on real hardware for complex, contact-rich tasks.

What you'll do#

• Develop and refine scalable frameworks for the transfer of human-object interaction skills to diverse robotic embodiments.
• Architect autonomous pipelines to process visual and human glove-collected data, extracting spatial and contact-rich information for generalist robot training.
• Implement state-of-the-art generative architectures to synthesize physically grounded, high-fidelity trajectories based on human reference motions.
• Explore cross-embodiment representations to enable joint training on human and robot data, improving generalization in unstructured environments.
• Research and optimize distillation and retargeting techniques to bridge the gap between simulation-trained policies and physical robotic deployment.

What you'll need#

• Master’s or Ph.D. in Robotics, Computer Science, Artificial Intelligence, Mechanical Engineering, Electrical Engineering, or related fields.
• Strong technical foundation in robot learning and control, including reinforcement learning, imitation learning, world modeling, or representation learning.
• Practical experience implementing and fine-tuning Generative Models and Transformer architectures.
• Hands-on experience with robotic manipulation systems, specifically involving contact-rich interaction, grasping, or multi-sensor perception such as tactile, force/torque, or proprioception.
• Proficiency in Python and modern machine learning frameworks like PyTorch, JAX, or TensorFlow.
• Experience with robotics middleware or simulation tools such as ROS/ROS2, MuJoCo, Isaac Sim, or PyBullet.

Location & details#

• Location: San Jose, California, United States
• Modality: On-site
• Type: Full-time
• Term: Rolling
• Compensation: $38.00 - $46.00 per hour