Research Scientist — Physical AI & World Models

Connect physics foundation models to robotics and world modeling, with a focus on learning physically consistent representations of dynamic systems.

• Research physics-informed world models for dynamic systems.
• Model state transitions, forces, trajectories, and interactions.
• Investigate how simulation-trained physics models improve robotic prediction and decisions.
• Evaluate conservation laws, geometric constraints, and temporal consistency.
• Build simulation-backed training and validation datasets.
• Explore model-based planning and reinforcement learning where appropriate.
• Collaborate on physical representations with geometric learning researchers.

• Strong foundation in machine learning, robotics, dynamics, or control.
• Experience with sequential, spatial, or dynamical learning.
• Proficiency in Python and PyTorch or JAX.
• Understanding of rigid-body dynamics, fluid dynamics, or simulation.
• Ability to run independent research and rigorous validation.

• MuJoCo, Isaac Sim, differentiable simulators, robotics benchmarks.
• Model-based RL or world-model research.
• Drones, autonomy, embodied AI, or relevant publications.

Demonstrate measurable gains in physical accuracy, generalization, or utility against high-fidelity simulation.

Send your CV and a relevant paper, technical project, GitHub repository, or portfolio to careers@ratiolabs.ai. Suggested email subject: “World Models and Robotics”.