Robotics Machine Learning Research Scientist – Large Behavior Models

Join a team focused on building general-purpose robots capable of dexterous manipulation through large-scale, multi-modal learning. You will develop data-efficient algorithms that fuse proprioception, vision, 3D representations, force, and tactile sensing to robustly control robotic systems. Scale learning with diverse data sources, including web-scale text, images, and video, and leverage high-quality simulation and synthetic demonstrations. Explore test-time computation, continual learning, memory, and multi-modal and language-guided reasoning to enable long-context tasks. Collaborate on code infrastructure, run experiments on simulated and real robots, and publish results in peer-reviewed venues and open-source projects. You will contribute to rapid prototyping, problem-driven research, and addressing fundamental robotics and ML challenges.