**Summary:** Meta is looking for a Research Scientist to join our MultiMedia team. We are seeking recognized experts in diffusion/flow-matching applied to image/video generative models. The ideal candidate will be passionate about advancing scientific research and applying it to develop novel distillation techniques. Our goal is to achieve state-of-the-art quality with the lowest possible latency, enabling adoption of generative models at global scale. **Required Skills:** Research Scientist, Multimedia - Image & Video (PhD) Responsibilities: 1. Lead, collaborate, and execute on research that pushes forward the state of the art in multimodal reasoning and generation research 2. Work towards long-term ambitious research goals, while identifying intermediate milestones 3. Directly contribute to experiments, including designing experimental details, implement reusable code, running evaluations, and organizing results 4. Contribute to publications and open-sourcing efforts 5. Mentor other team members. Play a significant role in healthy cross-functional collaboration 6. Prioritize research that can be applied to Meta's product development **Minimum Qualifications:** Minimum Qualifications: 7. Currently has or is in the process of obtaining a PhD in the field of Computer Science, Artificial Intelligence, or a related field 8. Experience in AI 9. Experience in diffusion / flow matching 10. Publications in areas of Machine Learning or Computer Vision 11. Experience implementing software and executing complex experiments involving large AI models and datasets 12. Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization throughout employment **Preferred Qualifications:** Preferred Qualifications: 13. Direct experience in generative AI and LLM research 14. First author publications experience at peer-reviewed AI conferences (e.g., NeurIPS, CVPR, ICML, ICLR, ICCV, and ACL) 15. Fluent in Python and PyTorch **Industry:** Internet