Summary
Shunshun Liu is a Graduate Research Assistant and PhD candidate in Materials Engineering at the University of Virginia, with nine years of experience applying explainable machine learning to accelerate materials discovery and design. He develops interpretable ML models, integrates symbolic regression and Bayesian inference with mechanistic models, and couples DFT-based calculations with adaptive learning to target properties in high-entropy alloys and thermal barrier coatings. Recent internships at Los Alamos National Laboratory and Seagate involved building automated graph deep-learning workflows and Monte Carlo Tree Search methods for inverse materials design, highlighting a rare blend of hands-on algorithm development and domain-specific simulation expertise. Holding an MS from the University of Pennsylvania and a BE from Wuhan University of Technology, he brings practical proficiency in Quantum ESPRESSO, many-body perturbation theory, and data-driven engineering. Notably, his work emphasizes interpretability—turning complex first-principles and ML outputs into actionable analytical models for materials engineers.
9 years of coding experience
Master of Science - MS, Materials Engineering, Master of Science - MS, Materials Engineering at University of Pennsylvania
Bachelor of Engineering - BE, Materials Science, Bachelor of Engineering - BE, Materials Science at Wuhan University of Technology
Doctor of Philosophy - PhD, Materials Engineering, Doctor of Philosophy - PhD, Materials Engineering at University of Virginia
English, Chinese