ML Research Scientist (GenAI)

Image and video generation for world model navigation, interaction and planning

You'd be joining a research team that focuses mostly on commercialization and demo with end-to-end ownership.

The team has a strong track record on a wide range of applications from audio to image and video generation, and on-device and server deployments, with publications in top venues as ICML, CVPR, ICCV, etc. We're expanding into PhysicalAI and world models for navigation, interaction and planning, and we are interested in candidates with experiences in a few of the following: generative models, diffusion/flow, model/architectural efficiency, reinforcement learning, robot navigation, planning and simulation, and physical demos.