Research Scientist Intern, Computer Vision

About the Role

The Video Intelligence team is seeking highly motivated Research Interns to join us in advancing the next generation of video generation technologies. The Video Intelligence team is an applied AI research team within the Facebook pillar, and is responsible for building state-of-the-art GenAI technology to empower video generation and understanding, enabling innovative AI-driven video creation experiences and enhancing our ability to comprehend video content. As a Research Intern, you will work alongside leading experts in computer vision, generative modeling, and multimodal learning, contributing to research projects at the frontier of developing advanced video generation models. Our work not only advances the academic field but also lays the groundwork for future video intelligence systems and applications.

Key Responsibilities

• Conduct research on advanced topics in video generation and understanding, including but not limited to text-to-video generative models, image-to-video generative models, video understanding models, unified native video generative models.
• Design, implement, and evaluate novel algorithms and model architectures.
• Collaborate closely with researchers and engineers across the Video Intelligence group and broader GenAI teams.
• Contribute to publications in top-tier conferences and journals in AI, computer vision, and machine learning.
• Present findings and share insights that help shape both ongoing research and future directions.

Requirements & Tech Stack

• Programming experience in Python.
• Hands-on experience in deep learning frameworks such as PyTorch.
• Experience working on generative models e.g. diffusion models, LLM, autoregressive transformers, etc.

Qualifications

• Proven track record of solid research achievements as demonstrated by grants, fellowships, patents, as well as publications at leading AI conferences such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, or SIGGRAPH.
• Strong track record of 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.
• Ability to quickly understand and identify the research opportunities behind real-world applications, select the appropriate ML methods to explore, and proactively drive the iterations based on clear analysis of the current results.
• Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment.