Berkeley, California, United States
• Conducted research in high fidelity modeling, specializing in graph neural networks and physics-informed machine learning techniques to advance predictive accuracy in various engineering simulations.
• Developed an AI-based GNN-PINN model, a pioneering approach that accurately predicts the failure analysis and performance of diverse components from 3D mesh data and underlying physical laws during simulation, optimizing efficiency and precision in engineering analysis.
• Collaborated closely with Mathworks MATLAB developers to enhance their deep learning toolboxes, contributing to the broader deep learning community by refining resources for researchers and practitioners in the field.