Postdoctoral AI Researcher in Power Systems

The Energy and Photon Science Directorate advances basic science that underpins discoveries and breakthroughs for energy systems. The appointment will be for a one-year with an opportunity for a one-year renewal to perform research in the area of electric power grids based on funding and individual performance. The successful candidate will contribute to the development of next-generation AI foundation models and AI-enabled workflows for electric applications. In particular, the position focuses on advancing GridFM, a grid foundation model for power systems. The role offers unique opportunities to contribute to cutting-edge research while helping translate AI innovations into real-world utility applications that support grid modernization, resilience, and large-scale electrification. Essential Duties and Responsibilities: Extend current GridFM capabilities for distribution networks Develop scalable graph-based machine learning or related models Expand training data generation capabilities Create benchmarks and test developed models Required Knowledge, Skills, and Abilities: Ph.D. in Computer Science, Electrical Engineering, Mathematics, Physics, or a related field. Strong background in machine learning and deep learning.   Experience with PyTorch, JAX, TensorFlow, or similar frameworks.   Some experience developing Graph Neural Networks (GNNs), Graph Transformers, or foundation-model architectures.   Familiarity with model training, fine-tuning, evaluation, and deployment.   Understanding of uncertainty quantification, model robustness, and physics-informed AI.    Experience with GPU computing and large-scale model training.   Demonstrated ability to conduct independent research.   Preferred Knowledge, Skills, and Abilities: Familiarity with distributed computing, HPC environments, and cloud platforms.   Experience building production-quality software and ML pipelines.   Familiarity with Git, CI/CD, containerization (Docker), and reproducible workflows.   Experience developing APIs and workflow orchestration systems.   Experience optimizing AI workloads for performance and scalability.   Basic knowledge of electric power systems, transmission/distribution networks, power flow, optimal power flow, contingency analysis, or grid planning.  Familiarity with tools such as PowerModels, MATPOWER, PSS/E, GridLAB-D, OpenDSS, or similar.  Experience with mathematical optimization, mixed-integer programming, stochastic optimization, or decision analytics.   Familiarity with Gurobi, CPLEX, Pyomo, JuMP, or related tools. Experience with LLM-based workflows, tool-calling agents, MCP architectures, retrieval systems, or AI copilots.   Familiarity with multi-agent systems and decision-support applications.   Other Information: Candidates must have completed all degree requirements by the commencement of employment. BNL policy requires that after obtaining a PhD, eligible candidates for research associate…