Research Scientist Intern, FAIR - Video Generation Self-Improvement (PhD)

Job description

Meta is seeking Research Interns to join the Fundamental AI Research (FAIR) team within Meta Superintelligence Labs (MSL). Our mission is to advance the science of intelligence and develop technologies that push the boundaries of AI. We are looking for individuals interested in video generation, post-training of large-scale models, and self-improving agentic systems to help build the perceptual and generative foundations for next-generation AI systems. This internship offers the opportunity to collaborate with a highly interdisciplinary team of scientists, engineers, and cross-functional partners, leveraging cutting-edge technology, resources, and research facilities. Our interns have the opportunity to make core algorithmic advances and apply their ideas at an unprecedented scale. We're especially interested in candidates with expertise across video generation, computer vision, and multimodal AI, including: Generative modeling for video (diffusion, flow matching, video synthesis) Post-training of large-scale video and multimodal models (SFT/RL, optimization, data curation) Multimodal understanding, reasoning, and generation Self-improving and agentic systems (multi-agent LLM/VLM systems, tool use, planning) Reward modeling and LLM/VLM-as-a-judge Our team at Meta AI offers twelve (12) to twenty-four (24) weeks long internships and we have various start dates throughout the year. To learn more about our research, visit https://ai.meta.com/research/.