PhD Research Intern - Robotics & Physical AI

What you'll do

• Extend interaction-understanding models and build closed-loop systems linking perception, planning, robot execution, monitoring, and replanning.
• Program and integrate robotic platforms; monitor execution, detect failures, and trigger replanning or redeployment.
• Design experiments and evaluate robustness across changing actors, objects, locations, timing, and environmental conditions.

What they ask for

• Currently pursuing a PhD in Robotics, Computer Science, AI, Computer Vision, Machine Learning, or a related field.
• Strong hands-on robotics experience, including programming, training, integrating, and debugging real robots.
• Familiarity with robotic perception, planning, control, or embodied AI systems.
• Strong software engineering skills; experience with modern deep learning frameworks such as PyTorch.

Nice to have

• Publications at top AI, computer vision, or robotics venues, such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, RSS, CoRL, ICRA, or IROS.
• Experience with vision-language models, video understanding, interaction recognition, embodied AI, robot learning, real-time systems, ROS / ROS2, simulation, motion planning, deployment outside simulation, healthcare-related domains, or limited, noisy, or weakly supervised data.

Tools

Python, C++, PyTorch, ROS / ROS2

AI focus

Research and prototype interaction-understanding and embodied AI systems that perceive physical-world events, decide when, where, and how robots should act, and monitor execution to support replanning.