Research Scientist Intern, AI Research - World Models (PhD)

Summary: Meta is seeking Research Interns to join the SAM team in the Multimedia Perception org of Meta Superintelligence Labs. The role involves advancing the field of artificial intelligence through research on generative AI and multimodal data, contributing to ongoing projects, and drafting research publications. Responsibilities: - Perform research to advance the science and technology of generative AI - Perform research that enables learning to predict and condition on multimodal data (video, 3D structures, primarily images, text, and other modalities like audio) - Brainstorm with research mentors, review literature and existing solutions of a challenging real-world research problem - Develop novel solutions, implement prototypes, and perform extensive experiments to test the proposed solutions in meaningful benchmarks and metrics, analyze the results and verify the conclusions - Contribute to ongoing research projects and impactful technology releases - Draft and polish research publications - Present research outcomes to internal and/or external audiences Required Qualifications: - Currently has, or is in the process of obtaining, a PhD degree in Computer Vision, Machine Learning, Artificial Intelligence, or relevant technical field - Research and/or work experience in Generative Modeling and Computer Vision. In particular: video generation, 3D/4D reconstruction, video and image understanding, vision-language foundation models, representation learning, and related areas - Research and/or work experience in Machine Learning or Deep Learning with applications to perception - Experience in Python, C++, or other related languages - Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment Preferred Qualifications: - Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading workshops or conferences in Computer Vision (CVPR, ECCV, ICCV), Speech & Language (ACL, EMNLP, ICASSP, NAACL), Machine Learning (NeurIPS, ICLR, ICML, AAAI) or Computer Graphics (SIGGRAPH) - Experience working and communicating cross functionally in a team environment - Experience advancing AI techniques, including contributions to open source libraries and frameworks - Experience in utilizing theoretical and empirical research to solve problems - Experience manipulating and analyzing complex, large scale, high-dimensionality data from varying sources - Intent to return to the degree program after the completion of the internship/co-op - Demonstrated software engineer experience via an internship, work experience, coding competitions, or widely used contributions in open source repo Required Skills: Generative Modeling, Computer Vision, Machine Learning, Deep Learning Important Skills: Python, C++ Nice-to-Have Skills: Cross-functional communication, Research publication, Team collaboration Benefits: Benefits