Research Intern: Vision & Generative AI for Video

NVIDIA Corporation (old); Santa Clara (CA); On-site; USD 52,000 - 129,000; Full time

Job summary

NVIDIA Corporation seeks an outstanding computer vision and deep learning intern researcher to join the Spatial Intelligence Lab in Santa Clara, CA. The role focuses on research with real-world impact and offers opportunities to publish.

The intern will work on generative AI for videos, reconstruction, simulation, video understanding, policy learning, reinforcement learning, and VLMs, with collaboration across teams and external researchers.

Qualifications

• Must be a second-year Ph.D. student in CS/Engineering, Mathematics
• Excellent knowledge of computer vision methods and deep learning
• Excellent programming skills in Python; C++ and parallel programming (CUDA)
• Knowledge of PyTorch or similar ML frameworks
• Outstanding research track record with publications in top venues (CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR)
• Excellent communication skills and Git proficiency

Responsibilities

• Research, design and implement methods for topics like generative AI for videos, reconstruction, simulation, video understanding, policy learning, RL, VLMs
• Publish original research at the end of the internship
• Collaborate with team members and with external researchers
• Contribute to ongoing projects and share results with the lab community

Skills

Python

C++/CUDA

PyTorch

CV/DL theory

Git

Communication

Education

PhD candidate (2nd year)

Tools

CUDA

Job description

NVIDIA Corporation seeks an outstanding computer vision and deep learning intern researcher to join the Spatial Intelligence Lab in Santa Clara, CA. The role focuses on research with real-world impact and offers opportunities to publish.

The intern will work on generative AI for videos, reconstruction, simulation, video understanding, policy learning, reinforcement learning, and VLMs, with collaboration across teams and external researchers.