About this role
Research role building multimodal models and systems for understanding complex environments, with research areas including video understanding, 3D and spatial reasoning, multimodal representation learning, generative modeling, and structured environment modeling. Ideal candidates have PhD-level research experience or experience building perception systems in industry; based in New York City, on-site.
Skills for this role
Computer VisionMultimodal LearningGenerative ModelingVideo Understanding3D ReasoningSpatial ReasoningMultimodal Representation LearningStructured Environment ModelingPerception SystemsSensor ModalitiesResearch