-
on the development and application of machine learning algorithms in areas such as surrogate modeling for physical systems, data assimilation, and scientific data reduction. The position comes with a travel allowance
-
journals and conferences. This role provides a unique opportunity to work with the world’s first exascale system, Frontier, and collaborate with leading experts in machine learning, optimization, electric
-
. Construct machine-learning models for feature-based molecular property prediction and drive the inverse design of ligands with engineered properties. Develop machine-learned interatomic potentials trained
-
essential. Experience in applying machine learning approaches particularly large language models. Ability to work within a multi-disciplinary team environment on scientifically challenging problems
-
Division (MSTD), Physical Sciences Directorate (PSD) at Oak Ridge National Laboratory (ORNL). Examples on areas of research interest include but are not limited to: AI/machine learning algorithm development
-
or novel applications of machine learning. Expertise in deep learning techniques such as transformers, LLM, GNN, generative models OR advance matrix method such as matrix/tensor completion, non-negative
-
simulations of reactor core, and other system components Develop reduced-order calibration approaches and apply machine learning and Bayesian calibration methods to enable multi-scale, multi-physics model
-
management machine learning, distributed computing, and resource optimization leveraging the unique computational resources available at ORNL, including the Frontier supercomputer—the world's first exascale
-
well as artificial intelligence and machine learning techniques (AI/ML) with emphasis on electronic properties (charge and spin) of a range of materials important to the DOE mission, including the materials classes
-
analytics, and machine learning, the Grid Interactive Controls group delves deeply into understanding intricate grid-edge operations. Researchers are dedicated to laying the groundwork for optimal X2G