I develop machine learning models and differentiable solvers to accelerate the mechanical design of meter-scale structures, such as buildings, long-span roofs, and bridges. Currently, I study how to embed structural mechanics into neural networks to build trustworthy generative models for nonlinear response prediction and inverse design for cost minimization and solution diversity. Previously, I worked on form-finding methods that translate architectural intent into lightweight and buildable structural systems via shape optimization. I hold a master’s degree from ETH Zurich and a Ph.D. from Princeton.