Sort by
Refine Your Search
-
A postdoctoral position on exascale atomistic simulations, AI/machine learning and data analysis of ferroelectric devices is available immediately at the Center for Nanoscale Materials (CNM
-
techniques to enable multimodal online monitoring of chemical and radiochemical separations processes Acquire fundamental data relevant to chemical separations in support of related modeling efforts Analyze
-
, inclusive, and accessible environment where all can thrive. Additional Preferred Qualifications: Working knowledge of power system protection and control. Familiarity with Machine Learning. Familiarity with
-
including transient analysis, engineered system evaluation, and machine learning applications in modeling thermal fluid behavior of interest to reactor analysis. The candidate is expected to produce papers
-
. Develop advanced optimization, control, or machine learning strategies for distribution systems; validate these strategies using hardware-in-the-loop or real-time grid simulators. Develop optimization
-
the performance and scalability of large-scale molecular dynamics simulations (e.g. LAMMPS) using machine-learned potentials (e.g. MACE) through algorithmic improvements, code parallelization, performance analysis
-
multidisciplinary team comprised of fellow postdoctoral appointees, experimentalists, and staff scientists, with computational fluid dynamics (CFD) and artificial intelligence/machine learning (AI/ML) expertise, with
-
-of-the-art data management, machine learning and statistics techniques. With the advancement of Exascale systems and the variety of novel AI hardware designed to accelerate both training and inference
-
with computer-aided design software. Knowledge of deep machine learning (using TensorFlow, PyTorch, etc.) for multi-fidelity modeling, regression tasks, management and analysis of large datasets, and
-
machine learning expertise, with the goal to enhance predictive capability and scalability of multi-scale and multi-physics simulation codes. Perform high-fidelity CFD simulations of complex physical