Postdoctoral Research Associate -AI for Science

Requisition Id 17200

About the role

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.

Responsibilities

• 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

Requirements

• 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.
• Applicants cannot have received their Ph.D. more than five years prior to the date of application and must complete all degree requirements before starting their appointment.
• The appointment length will be up to 24 months with the potential for extension.