Research Scientist, Robotics & Embodied AI

Description

Develop Vision Language Action (VLA) models that combine Gemini's world understanding with physical actions to directly control robots. Create reasoning and agentic systems for the physical world, enabling robots to perform tasks, respond to their environment, achieve dexterity, and reason over multi-step tasks. Partner with robotics companies to bring this intelligence to applications at scale, advancing areas of general purpose robotics including real world understanding, action generalization, and human-robot interaction.