Research Scientist Intern, Large Foundation Models and Generative AI (PhD)

The Meta Reality Labs Research Team is composed of world-class researchers, developers, and engineers dedicated to shaping the future of AR/VR and machine perception. The Surreal Vision group at RL Research is seeking exceptional Research Scientist interns to contribute to the development of an egocentric AI system. This system will form the foundation for contextual-AI-enabled AR devices and humanoid robots. As a research intern, you will tackle cutting-edge research challenges, innovating novel computer vision and machine learning techniques. Your research project may cover or relate to the following topics: - Egocentric vision language model for long-context 3D scene understanding - Utilizing memory for more consistent and accurate future state prediction using visual language action models or world models - Exploring novel learning strategies to improve the quality and generalization of visual language action models or world models with egocentric data - 4D generation & reconstruction of dynamic scenes Our internships are twelve (12) to twenty four (24) weeks long and we have various start dates throughout the year. Some projects may require a minimum of 24 consecutive weeks.