Postdoctoral Researcher in Scientific Machine Learning and Cross-scale Predictive Modeling

Golden, CO

Remote Site

Full time

R14604

Postdoctoral Researcher in Scientific Machine Learning and Cross-scale Predictive Modeling

CO - Golden

Postdoc (Fixed Term)

40

NLR is located at the foothills of the Rocky Mountains in Golden, Colorado is the nation's primary laboratory for energy systems research and development.

Join the National Laboratory of the Rockies (NLR), where world-class scientists, engineers, and experts are accelerating energy innovation through breakthrough research and systems integration. From our mission to our collaborative culture, NLR stands out in the research community for its commitment to an affordable and secure energy future. Spanning foundational science to applied systems engineering and analysis, we focus on solving complex challenges to deliver advanced, secure, reliable, and cost-effective energy solutions.

Our work helps strengthen U.S. industries, support job creation, and promote national economic growth.

At NLR, you'll find a mission-driven environment supported by state-of-the-art facilities, multidisciplinary research teams, and strong collaborations with industry, academia, and other national laboratories. We offer robust professional development opportunities, and a competitive benefits package designed to support your career and well-being.

The Artificial Learning and Intelligent Systems group in NLR’s Computational Science Center has an immediate opening for a Postdoctoral Researcher to pursue a cross-disciplinary research project in cross-scale learning from heterogeneous evidence (lab-scale to pilot-scale) relevant to the DOE Office of Critical Minerals and Energy Innovation.

The successful applicant will develop methods that combine evidence across different experimental scales, conditions, and modalities to make predictions at unseen physical or operational scales where data may be sparse or unavailable. In this context, the relationships between inputs and outputs may change with scale, and the available data may come from different data sources with different modalities and amounts and have different physical contexts.

We are looking for someone who has developed innovative learning methods, including multi-modal and surrogate modeling approaches, transfer learning techniques, physics-informed ML, and/or statistical learning methods.

Must be a recent PhD graduate within the last three years.

*** Must meet educational requirements prior to employment start date.**

• Demonstrated experience developing ML models for scientific or engineering systems
• Demonstrated experience in learning from one set of conditions or domains and predicting in another, including situations where the source and target distributions differ.
• Demonstrated experience in combining data with different modalities, sampling rates, resolutions, fidelities, measurement characteristics, costs, accuracies, or experimental conditions.
• Demonstrated experience in physics-informed and hybrid modeling, showing the ability to incorporate mechanistic models, physical constraints, or known relationships when useful, without assuming that complete physics models are available.
• Demonstrated experience in model representation and adaptation, how to represent changes in system context, operating conditions, geometry, or scale so that the model can distinguish what is transferable from what is not.
• Excellent communication skills
• Demonstrated experience working in multi-disciplinary teams and collaborative software development
• Demonstrated experience with python and version control

The anticipated closing window for application submission…