Research Scientist Intern, Computer Vision - Video Intelligence (PhD)

Meta•Menlo Park, CA

9d•$7,650 - $12,667

About The Position

The Video Intelligence team, an applied AI research team within the Facebook pillar, develops generative AI technology for video generation and understanding. The team works to enable AI-driven video creation experiences and improve video comprehension. As a Research Scientist Intern, you will work with experts in computer vision, generative modeling, and multimodal learning on research projects focused on advanced video generation models. The work contributes to academic research and supports the development of future video intelligence systems and applications.

Requirements

Currently hold or be pursuing a Ph.D. in Computer Science, Electrical Engineering, or a related field, focused on generative modeling, computer vision, or machine learning.
Programming experience in Python and hands-on experience with deep learning frameworks such as PyTorch.
Experience working with generative models, such as diffusion models, LLMs, or autoregressive transformers.
Must obtain work authorization in the country of employment by the time of hire and maintain work authorization during employment.

Nice To Haves

Intent to return to the degree program after completing the internship or co-op.
Research achievements demonstrated by grants, fellowships, patents, or publications at leading AI conferences such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, or SIGGRAPH.
Contributions to open-source projects, benchmarks, or shared research artifacts.
Research experience in video generation, temporal modeling, multimodal learning, or unified native video generative models.
Experience working and communicating cross-functionally in a fast-paced team environment, with the ability to identify research opportunities in real-world applications, select appropriate machine-learning methods, and proactively iterate based on analysis of results.

Responsibilities

Conduct research on advanced video generation and understanding, including text-to-video and image-to-video generative models, video understanding models, and unified native video generative models.
Design, implement, and evaluate novel algorithms and model architectures.
Collaborate with researchers and engineers across the Video Intelligence group and broader GenAI teams.
Contribute to publications in leading AI, computer vision, and machine learning conferences and journals.
Present findings and share insights to inform current research and future directions.