Research Scientist

Job description

Job responsibilities

• Advance the Frontier: Design and implement state-of-the-art robot learning algorithms (RL, Imitation Learning, Diffusion) for complex, high-DOF manipulation tasks.
• VLA & Video Generation: Architect and scale multi-modal foundation models (VLMs/VLAs) and leverage generative video architectures to enhance world-modeling and robot foresight.
• End-to-End Ownership: Own the full research-to-production pipeline: from task definition and data curation to large-scale training and real-time deployment on physical hardware.
• Physical-World Evaluation: Move beyond the benchmark. You will evaluate and iterate on models using our expanding robot fleet, ensuring commercial-grade performance in dynamic customer environments.
• Collaborative Leadership: Work at the intersection of AI, Hardware, and Teleop teams to enhance the "Intelligence-per-Watt" of our robotic systems.