I focus on mechanics-informed generative design approaches that fuse topology optimization with AI to propose novel material architectures satisfying complex mechanical targets before fabrication. This includes inverse design, multiscale surrogate modeling, and metamaterials development to accelerate materials engineering innovations
My research addresses real-time sensing and control strategies in metal 3D printing processes such as Directed Energy Deposition (DED) and Laser Powder Bed Fusion (LPBF). The goal is to enable AI-augmented, closed-loop platforms for functionally graded materials with optimized process parameters and microstructure control.
I develop advanced generative models—including GANs, diffusion models, and normalizing flows—to learn process–structure–property linkages. These models enable rapid microstructure prediction and inverse design, accelerating materials discovery and characterization by coupling synthetic data generation with surrogate property prediction.
I aim to build autonomous materials discovery platforms integrating automated microscopy, robotics, and AI-driven experimental design. These self-driving laboratories enable closed-loop experimentation with human-in-the-loop feedback to accelerate materials development cycles and optimize complex systems efficiently.