PhD Research Intern, Generative AI - 2026
Core
Research in generative AI, multimodal foundation models, world models, and embodied AI to advance Physical AI and world models.
Role type
PhD Research Intern (Generative AI / Physical AI)
Builds
Algorithms for video understanding/generation, action-conditioned simulation, multimodal reasoning, and policy learning.
Domain
Generative AI, Robotics, Autonomous Driving, Simulation
Deliverable
research
Required skills
Generative AI, Computer Vision, Multimodal Learning, Robotics, Reinforcement Learning, Python, PyTorch
Preferred skills
Large-scale foundation model training, Video models, VLMs, World models, Distributed training
Responsibilities
Conduct research in generative AI and multimodal foundation models; Develop algorithms for video understanding and simulation; Train and evaluate large-scale models using video, image, language, and robotics data; Collaborate with researchers and engineers across AI, robotics, and graphics teams; Publish research at top conferences and transfer innovations into products.
