-
: The design and analysis of computational methods that accelerate AI/ML when applied to large scientific data sets; Energy efficient physics-aware algorithms, capable of distributed learning on high performance
-
Methods and Dynamics (MMD) Group at Oak Ridge National Laboratory (ORNL) is seeking several qualified applicants for postdoctoral positions related to Computational Methods for Data Reduction. Topics
-
analytical methods and finite element analysis packages to prove designs meet established design standards. Provide hand calculations to support the design. Prepare schedules, cost estimates, status updates
-
intelligence, and architecture-aware algorithms that harness machines, ideas, and data to enable far reaching scientific breakthroughs. We develop computer innovations and advanced practical tools to address
-
Requisition Id 15420 Overview: The Multiscale Methods and Dynamics (MMD) Group at Oak Ridge National Laboratory (ORNL) is seeking several qualified applicants for postdoctoral positions related
-
detection, and power grid waveform analytics. You will apply methods traditionally used in wireless communications and signal intelligence — including time-frequency analysis, interference modeling, multi
-
computational physics, computational materials, and machine learning and artificial intelligence, using the DOE’s leadership class computing facilities. This position will utilize methods such as finite elements
-
the National Security Sciences Directorate at ORNL. CRID provides new methods, tools, and strategies to detect and mitigate adversarial attacks on critical infrastructure and protections and informs national
-
Requisition Id 15422 Overview: The Multiscale Methods and Dynamics (MMD) Group at Oak Ridge National Laboratory (ORNL) is seeking several qualified applicants for postdoctoral positions related
-
physics-informed and physics-ML hybrid approaches that integrate domain knowledge with data-driven methods to advance hydrological process understanding and prediction. Conduct multimodal, multiscale data