About this role
Our mission is general causal intelligence; AI that is capable of (1) predicting the future and (2) identifying the actions to alter it.
To achieve this breakthrough, 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.
We look for domain experts who are excited to tackle unsolved problems. Weather is our first proving ground — the most well-observed physical system on Earth — and getting it right demands deep atmospheric expertise embedded directly in the research. Your mission is to bring that expertise to bear on every part of the model: what data we learn from, how we know the model is correct, and where it still falls short.
Responsibilities
Guide the sourcing and validation of atmospheric data, advising on observation systems, their characteristics, and their pathologies
Define what forecast quality means, bringing rigorous verification methodology to how we evaluate the model
Run case studies on high-impact events to probe model behavior and surface failure modes
Benchmark against operational numerical weather prediction baselines and the state of the field
Partner with model, evaluation, and product teams to translate atmospheric expertise into research direction and credible results
What we're looking for
We value a relentless approach to problem-solving, rapid execution, and the ability to quickly learn in unfamiliar domains.
Deep expertise in atmospheric science, meteorology, or a closely related field (typically a PhD or equivalent research experience)
Familiarity with operational forecasting, numerical weather prediction, and forecast verification methods
Comfort working with large observational and reanalysis datasets
Ability to collaborate closely with ML researchers and translate domain knowledge into technical requirements
A rigorous, evidence-driven approach to evaluating model quality