Research

At Prometheus Materials, I led R&D efforts in inverse materials design, leveraging genetic algorithms and machine learning to optimize novel concrete mix formulations based on cost, performance, and global warming potential (GWP) metrics. I developed predictive models for estimating concrete strength and biomineralization byproducts, maintained and improved centralized databases and internal infrastructure, and designed and deployed web-based tools for data analysis and visualization. These tools supported both materials science and biotechnology research initiatives across the company.

As a Postdoctoral Scholar in the Koes Group I focused on modeling protein–ligand interactions to support structure-based drug discovery. My work centered on using enhanced sampling molecular dynamics and molecular docking techniques to analyze protein systems and enable virtual screening of large chemical libraries. This experience deepened my understanding of computational biophysics and expanded my skills in pipeline development for drug discovery applications.

During my Ph.D. in the Hutchison Group I applied computational chemistry and optimization algorithms to study molecular conformers and design materials for energy storage. I explored the use of machine learning and Bayesian optimization to improve search strategies such as genetic algorithms, with a particular focus on accelerating the discovery of materials with desirable quantum mechanical properties.