Postdoctoral - Reduced Order Modeling - Research Staff Member
Core
Develop fast, trustworthy, and data-efficient surrogate models integrating physics-based simulations with experimental data for automated scientific workflows.
Role type
Postdoctoral Research Staff Member (Scientific Machine Learning & Reduced-Order Modeling)
Builds
Surrogate and reduced-order models, AI-agent-assisted scientific workflows, and computational tools for electrochemical systems and advanced manufacturing.
Domain
Computational Science / Scientific Machine Learning / Physical Systems Modeling
Deliverable
production ML models
Required skills
scientific machine learning, reduced-order modeling, surrogate modeling, system identification, uncertainty quantification, active learning, optimization, numerical methods, data-driven modeling of physical systems
Preferred skills
equation discovery, hybrid physics/data-driven modeling, sensitivity analysis, adaptive experimental design, high-performance computing, modern machine-learning frameworks (PyTorch, JAX), AI agents, Model Context Protocol
Technologies
Python, C++, C, FORTRAN, PyTorch, JAX
Responsibilities
Develop data-efficient computational methods for predictive models from simulation and experimental data; reconcile computational models with physical experiments via parameter calibration and model-discrepancy correction; identify low-dimensional parameter spaces and latent representations; develop uncertainty-aware surrogate models; investigate active-learning and adaptive experimental-design strategies; integrate models with AI-agent-compatible software interfaces; design and perform numerical experiments to evaluate model accuracy and performance; publish research results in peer-reviewed journals.
Seniority
Postdoctoral (PhD required, independent research)
