I am a graduate student in Mechanical Engineering at Clemson University, working in the CEDAR Group. My research sits at the intersection of engineering design and geometric deep learning: I build models that learn directly from 3D geometry and simulation data to support core engineering tasks such as generative design and surrogate modeling. I aim to bridge the gap between computational intelligence and human creativity by developing tools that help engineers explore large design spaces, understand performance trade-offs, and make better design decisions on real hardware.

Currently, my work focuses on deep learning models that operate on automotive hood frame geometries, learning the relationship between shape and structural performance from simulation data. These models are used for fast surrogate prediction and design generation, enabling engineers to evaluate many more alternatives in less time and ultimately arrive at lighter, safer, and more efficient designs.