I am a Computer Scientist in the AI/ML Group at Argonne National Laboratory (ALCF). My research interests include agentic AI systems for autonomous scientific discovery, large-scale distributed training, and data management for AI. I apply high-performance computing and deep learning to domain sciences including physics, chemistry, and materials science. I co-lead the MLPerf Storage Benchmarking group, developing benchmark suites for evaluating the performance of storage systems for AI applications.
My current projects include: (1) ExaIO/ExaHDF5 — developing advanced features in the HDF5 library for efficient parallel I/O, including caching and pre-staging on node-local storage and topology-aware collective I/O; (2) data management and I/O optimization for AI workloads; (3) scalable image reconstruction algorithm development; and (4) agentic AI workflows for autonomous scientific discovery across DOE leadership computing facilities.
I received my Ph.D. in Physics from the University of Illinois at Urbana-Champaign in 2016, with a strong background in condensed matter physics, density functional theory, and Quantum Monte Carlo. I joined ALCF as a Theta Early Science postdoc in 2016, working on developing and scaling density functional theory and many-body perturbation theory. In 2018, I joined the AI/ML Group, expanding my expertise in data science and machine learning.
I grew up in a small village in southern China, where both of my parents are farmers. My curiosity about nature led me to pursue physics through a Ph.D.; deeper questions about meaning eventually led me to faith. I became a Christian in Hong Kong in 2010, and I find that work, family, and personal life are all means to grow and find purpose.
I live in Glen Ellyn, IL with my wife and two children. Outside of work I enjoy hiking, walking in nature preserves, and distance running — I have completed seven full marathons.
I mentor students and postdocs through ALCF’s summer internship and postdoctoral programs. Past and current mentees have worked on topics including parallel I/O optimization, benchmarking AI workloads, deep learning for materials science, and agentic workflow systems.
I am always interested in collaborations at the intersection of HPC, scientific AI, and autonomous workflows. If you are a student, postdoc, or external researcher with a project connecting to my research areas, I would be happy to hear from you.