Tianshu Wen has been a Photonics Design Engineer at Applied Materials, Inc. since 2025. Previously, he interned at Lorentz Solution, Inc. (2024) and Lawrence Livermore National Laboratory (2023). He received his Ph.D. in Aerospace and Mechanical Engineering from the University of Notre Dame in 2024, where he was advised by Matthew J. Zahr. He also holds an M.S. in Applied Mathematics from the University of Notre Dame (2023), an M.S. in Mechanical Engineering from Washington University in St. Louis (2019), and a B.S. in Mechanical Engineering from Central Michigan University (2016). He specializes in numerical optimization, model order reduction, deep learning, computational fluid dynamics, and finite element methods.

At Applied Materials, Inc., he is working on improving the in-house optimizer to handle multi-objective topology optimization for a better Pareto front. Meanwhile, he is also developing deep learning models for forward and inverse problems in photonics design.

At Lorentz Solution, Inc., he implemented and optimized a block-accelerated direct solver for large-scale dense linear systems, achieving a ~5x speedup over the Intel MKL library.

At Lawrence Livermore National Laboratory (LLNL), he developed an implicit neural representation (INR) based reduced-order model for nonlinear PDEs, achieving a speedup of up to 1500x compared to using a full-order model.

At the University of Notre Dame, he developed a globally convergent method to accelerate large-scale PDE-constrained optimization using on-the-fly model reduction, achieving a speedup of up to 18x compared to traditional optimization methods.

Experiences

Publications

Journal Articles

Conference Proceedings

Workshop Papers

Talks

Accomplishments

CV