PhysicsX · posted · checked
Simulation Engineer (CFD) – Large Physics Models
Hybrid · LondonJunior
Who can apply
Hybrid · London
Location: London, United Kingdom
About us
Re-architecting Engineering for the Age of Intelligence
PhysicsX is the physics AI company for industrials. The company’s mission is to accelerate hardware innovation by overhauling what industrial engineering and manufacturing look like today. PhysicsX is building a new simulation software stack to deliver deep physics AI enablement across the entire engineering lifecycle. The company partners with leading organisations in aerospace & defence, automotive, semiconductors, materials, and energy & renewables, supporting them on some of their most critical and complex challenges. PhysicsX is headquartered in the United Kingdom, with offices in London, New York, and Singapore and an expanding presence in the Bay Area.
About the role
Large Physics Models need data, and the quality, diversity and cost of that data shape is what we need to define. As a Simulation Engineer in our Research team, you will build the simulation side of that foundation. You’ll work in a research environment, alongside ML researchers and engineers, on how physics-based simulation and machine learning can be combined in ways that haven’t been done before.
You’ll be working at the frontier of Large Physics Model development, shaping new AI paradigms for our customers to benefit from in the future. You will aid in data generation, how, and at what fidelity, so that the models we build are both accurate and affordable to train.
What you will do
Generate simulation data for training large-scale ML models, drawing on a mix of methods and fidelity levels.
Scientific computing in GPU frameworks such as JAX and Nvidia Warp.
Work with multi-fidelity data: understand tradeoff between fidelity and CFD simulators and how the two can be combined.
Use commercial and open-source CFD tools to produce reference data
Collaborate closely with ML researchers and engineers, translating between the physics and the models, and helping the team get the best corpus possible.
Contribute to the technical direction of our data generation work and flag the simulation investments that will unlock research progress.