I am an Applied Scientist whose work sits at the intersection of physics-based modeling and modern machine learning for subsurface and energy systems. I completed a joint Ph.D. in Physics and Data Science at Harvard University and the University of Science and Technology Beijing, where I developed Physics-Informed Neural Networks (PINNs) for energy-sector optimization and pore-network simulation methods for characterizing multiphase flow, including CO₂–brine relative permeability. My research centers on AI-enabled approaches to reservoir engineering—coupling first-principles physics with data-driven surrogates to accelerate reservoir simulation, sharpen history matching, and optimize production and storage strategies under uncertainty. At Schlumberger, I applied PINNs and large-scale distributed computing to real-world energy optimization problems, and my broader work spans multi-modal Transformer architectures, scientific high-performance computing, and surrogate modeling for engineering simulation.