Odyssey is looking for people with a deep interest in improving machine learning algorithms at the intersection of diffusion world models and robotics. Interactive, action-conditioned world models are a cutting-edge research area that is not yet mature. You will be working at the cusp of what’s possible, using world models as simulators, feature extractors, and training grounds for real robot policies and model-based RL approaches. Most new experiments here will fail; your focus will be on maximally learning from failed experiments to increase the chances of eventual success on real hardware.