About the Role
We are building a Large Physics foundation Model (LPM) to achieve general causal intelligence, capable of predicting the future and identifying actions to alter it. Our mission is to ensure the model evolves towards this thesis: grounded in physical law, evaluated against it, and ready to generalize across domains.
Responsibilities
- Assess model consistency with conservation laws and physical constraints.
- Develop evaluations to test physical coherence of model behavior.
- Advise on the physics of modeled systems, including fluid dynamics and thermodynamics.
- Investigate LPM generalization across physical domains.
- Connect physical understanding to research direction in collaboration with other teams.
Requirements
- Relentless approach to problem-solving.
- Rapid execution.
- Ability to quickly learn in unfamiliar domains.
- Deep expertise in physics (e.g., fluid dynamics, thermodynamics, computational physics).
- Familiarity with numerical simulation of physical systems (e.g., CFD) and its trade-offs.
- Interest in the intersection of machine learning and physical modeling.
- Ability to collaborate with ML researchers and translate physical principles into technical requirements.
- Rigorous, evidence-driven approach to evaluating model quality.
Experience Level
- PhD or equivalent research experience in physics
Education Level
- PhD or equivalent research experience
About the Company
- Our mission is general causal intelligence; AI that is capable of (1) predicting the future and (2) identifying the actions to alter it.
- We are building a Large Physics foundation Model (LPM) because physical systems, unlike text or images, are governed by verifiable cause and effect.
- We believe that scaling on physics will enable an understanding of causality required to predict and control physical systems, starting with weather.
- Our founding team has built and deployed AI against the physical world in robotics, drug discovery, and particle physics at institutions like DeepMind, Waymo, Cruise, Insitro, Nabla Bio, and CERN.
