Location: Lemont, IL
Cap-Exempt H-1B Position — No lottery required
The Industrial Technologies Group within the Energy Systems and Infrastructure Assessment (ESIA) Division at Argonne National Laboratory seeks a highly qualified Postdoctoral Appointee to conduct applied research on AI-driven and AI-enhanced industrial energy systems optimization modeling, material flow analysis, and supply chain analysis of industrial commodities and critical materials. The successful candidate will contribute to Argonne’s industrial capacity planning, logistics optimization, and supply chain analysis models and apply these tools to support high-impact research on resilient, competitive, and energy-efficient U.S. manufacturing systems. The appointee will be expected to lead core model development and as needed, help expand capabilities in co-optimization of industrial end-use and energy supply systems, multi-objective and stochastic optimization, advanced statistical analysis, and data visualization. This position offers the opportunity to work with a multidisciplinary team of computational scientists, economists, engineers, and other researchers to develop data-driven, decision-relevant analytical tools for complex industrial systems. Key Responsibilities: - Develop, improve, and apply computational models for industrial capacity planning, logistics optimization, material flow analysis, and supply chain analysis. - Apply artificial intelligence, machine learning, LLMs, and advanced statistical techniques to industrial energy systems, manufacturing systems, and commodity supply chains. - Integrate data-driven methods with optimization-based modeling frameworks, including linear, mixed-integer, stochastic, robust, and multi-objective optimization. - Conduct analyses of industrial system resilience, competitiveness, and operational performance under uncertainty. - Support model development for co-optimization of industrial end-use systems and energy supply systems. - Build reproducible computational workflows for data processing, model development, c