Conducting research across two distinct verticals: Scientific Machine Learning (SciML), where I integrate physics priors with AI for design optimization, and Generative AI, where I focus on hallucination detection and reliability in LLMs for non-physical domains like healthcare.

Building a foundational framework for the inverse design of granular architected materials using Generative AI. This work unifies granular physics with large-scale generative learning to enable data-efficient discovery of mechanically programmable systems.

Conducted finite element modeling of laminated composite plates under thermal and dynamic loading, extending the work to include hygrothermal coupling effects.

Developed a MATLAB-based algorithm for estimating dynamic parameters of structures under seismic excitation.

Creating a specialized curriculum on AI for Continuum Materials, designed to demystify the integration of deep learning methods with Physics. The series will demonstrate how to solve continuum and discrete systems using Physics-Informed Neural Networks, Universel Differential Equations and Generative AI Models.

Presented my research journey and publication history as a case study for aspiring researchers. Dissected strategies for identifying high-impact problems and building a coherent academic portfolio.

Delivered an invited technical lecture on non-reciprocal metamaterials for the course Wave Propagation in Designed Materials. Covered dispersion relations and the Skin Effect in mechanical lattices.