Physics-Informed Machine Learning - Postdoctoral Researcher
Core
Develop and apply advanced computational methods, specifically physics-informed machine learning, to model complex physical systems and improve scientific simulations.
Role type
Postdoctoral Researcher (Physics-Informed Machine Learning)
Builds
Physics-informed models, surrogate models, reduced-order models, and scientific simulations for the Atmospheric, Earth and Energy Division.
Domain
Computational mechanics, scientific machine learning, and numerical methods.
Deliverable
production ML models
Required skills
Physics-informed machine learning, computational mechanics, numerical methods, neural networks, high-performance computing, Python, PyTorch/JAX/TensorFlow
Preferred skills
Physics-informed neural networks, neural operators, differentiable programming, deep learning, transfer learning, generative models, finite-element methods, computational fluid dynamics, solid mechanics, multiphysics simulation
Responsibilities
Develop physics-informed ML methods for computational mechanics; Integrate governing equations and constraints into ML models; Develop, train, and evaluate neural networks and surrogate models; Analyze computational and experimental data; Perform computational mechanics simulations; Publish research results in peer-reviewed journals and present at conferences.
Seniority
Postdoctoral (early career researcher)
