Postdoctoral Research Associate -AI Science

Select how often (in days) to receive an alert:

Oak Ridge National Laboratory is the largest US Department of Energy science and energy Laboratory, conducting basic and applied research to deliver transformative solutions to compelling problems in energy and security.

The Discrete Algorithms Group at Oak Ridge National Laboratory (ORNL) is seeking a postdoctoral researcher for a two-year position specializing in artificial intelligence for science, knowledge-guided machine learning, and scalable scientific AI workflows. The successful candidate will conduct research at the intersection of machine learning, high-performance computing, scientific modeling, and domain-informed AI to accelerate discovery across DOE mission areas such as energy, materials, biology, nuclear science, autonomous laboratories, and scientific computing.

This position is motivated by emerging national priorities in AI for science, including the DOE Genesis Mission: transforming science and energy through AI-enabled research and development workflows. The successful candidate will develop novel AI methods that integrate scientific knowledge, simulation, experimental data, and large-scale computing to achieve measurable AI advantage in scientific discovery. Research directions may include scientific foundation models, physics- and knowledge-guided machine learning, graph and geometric learning, surrogate and reduced-order modeling, uncertainty-aware AI, autonomous experimentation, scientific agents, and scalable AI workflows for heterogeneous high-performance computing environments.

The successful candidate will design, implement, and evaluate AI methods that couple data-driven learning with scientific principles, constraints, ontologies, knowledge graphs, simulations, and experimental feedback. This role offers an exceptional opportunity to pursue an ambitious research agenda that advances trustworthy, interpretable, and scalable AI for science while collaborating with leading experts in machine learning, optimization, scientific computing, domain sciences, and high-performance computing.

The candidate will have opportunities to work with world-class computing resources, including ORNL’s leadership-class computing ecosystem, and to contribute to AI-enabled scientific workflows that address high-impact national challenges.

• Develop novel AI, machine learning, and knowledge-guided learning algorithms for scientific discovery and DOE mission applications..
• Design scientific AI workflows that integrate simulation, experimental data, domain knowledge, and high-performance computing..
• Develop methods for incorporating scientific constraints, conservation laws, mechanistic models, knowledge graphs, ontologies, and expert knowledge into machine learning systems.
• Investigate scientific foundation models, surrogate models, digital twins for different scientific disciplines

• A PhD in Computer Science, Applied Mathematics, Computational Science, or related discipline.
• Demonstrated hands-on experience and understanding of developing and applying HPC algorithms to scientific and ML models.
• Demonstrated research experience with AI and ML techniques.

• Experience with knowledge-guided machine learning, physics-informed machine learning, scientific foundation models, graph neural networks, geometric deep learning, operator learning, generative models, or AI agents.
• Knowledge of HPC matrix, tensor and graph algorithms.
• Knowledge on distributed algorithms using MPI and other frameworks such as NCCL.
• Knowledge of high-performance computing and its applications.

Applicants cannot have received…