Posting Title
Postdoctoral Researcher in Numerical Optimization and Experimental Design .
Location
CO - Golden .
Position Type
Postdoc (Fixed Term) .
Hours Per Week
40 .
Working at NLR
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.
Job Description
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 optimization and adaptive experimental design for cross-scale scientific applications (lab-scale to pilot-scale) relevant to the DOE Office of Critical Minerals and Energy Innovation.
The successful applicant will develop optimization and sampling methods that leverage predictions from models that were trained on cross-scale heterogeneous evidence and their corresponding uncertainties. The sampling strategies must determine which experiments to run, which measurements to collect, or operating conditions to use in order to acquire the most information for improving model predictions at the target experimental scale. The successful applicant will develop original methodologies and have expertise in numerical optimization, optimal experimental design, active learning and Bayesian optimization, sequential decision-making and information theory, adaptive sampling and surrogate-based optimization, and statistical design of experiments. The ability to address challenges arising from applications with noisy, messy, missing or sparse data, and dealing with models that have uncertainty is a must.
.
Basic Qualifications
Must be a recent PhD graduate within the last three years.
* Must meet educational requirements prior to employment start date.
Additional Required Qualifications
Demonstrated experience in developing optimal experimental design strategies with strong background in selecting experiments to maximize information, identify parameters, distinguish hypotheses, or improve model predictions.
Demonstrated experience in developing active learning and sequential design methods for iteratively selecting new data points based on what has already been learned.
Demonstrated experience in Bayesian optimization, including development of acquisition functions, surrogate models, and sequential optimization, ideally beyond standard black-box optimization.
Demonstrated experience with multi-fidelity, multi-modal, multi-source sampling including making optimal decisions on where to sample, what conditions to test, which scale (lab to pilot) or level of fidelity to conduct an experiment.
Understanding of information theory and decision theory with deep understanding of information gain, value of information, and the relationship between uncertainty reduction and practical decisions.
Understanding of constrained and cost-aware sampling methods including accounting for experiment cost, time, feasibility, safety, and operational…