Postdoctoral Research Associate - AI Models for Power Grid System

About the role

The Computational Coupled Physics (CCP) Group within the Computational Sciences and Engineering Division (CSED), at Oak Ridge National Laboratory (ORNL) is seeking a Postdoctoral Research Associate to develop, scale, and apply artificial intelligence (AI) and deep learning (DL) models for power grid systems.

Responsibilities

• Participate in the design, implementation, and deployment of scalable AI/DL models for power grid systems, including surrogate models and foundation-model workflows for OPF and related grid simulation tasks.
• Develop and maintain HPC-ready software workflows for distributed training, large-scale inference, scalable data ingestion, and data management on leadership-class computing systems and institutional clusters.
• Write robust Linux bash scripts and job submission scripts for SLURM and PBS environments, including multi-node GPU/CPU workflows, monitoring, restart, and post-processing pipelines.
• Author peer reviewed papers for journals and conferences, technical reports, open-source software, and represent the organization by making technical presentations at workshops and conferences.
• Collaborate within a multi-disciplinary research environment consisting of computational scientists, computer scientists, electrical engineers, domain scientists, and applied mathematicians conducting basic and applied AI/DL research in support of the Laboratory’s missions.

Qualifications

• A PhD in computer science or an AI-related field completed within the last 5 years.
• Demonstrated expertise in scalable deep learning, including distributed training and/or large-scale inference using modern AI frameworks such as PyTorch.
• Demonstrated experience with high-performance computing systems, including multi-node workflows on CPU and/or GPU clusters.
• Demonstrated expertise in scalable data management for AI/ML workflows, including efficient data preprocessing, storage, streaming, and I/O for large scientific datasets.
• Demonstrated experience writing SLURM and PBS job submission scripts for HPC clusters, including batch workflows, job arrays, environment setup, and restart logic.
• Demonstrated expertise with the Linux operating system, bash scripting, Git, Python, and reproducible software environments.
• Demonstrated expertise in writing advanced software in Python and in the design and implementation of deep learning algorithms.
• Expertise in object-oriented programming, scripting languages, and modern software engineering practices for research codes.
• Demonstrated effective written and oral communication skills, a proven publication record, and effective interpersonal skills.