I am a Machine Learning Scientist on the PDMB team at Merck, based in Cambridge, MA. My work focuses on developing agentic AI ecosystems and machine learning methods to accelerate translational modeling (a quantitative process that translates nonclinical data into clincal predictions).

Before joining Merck, I completed my PhD at Purdue University, where my work sits at the intersection of theoretical chemistry, computational biology, and generative machine learning. My research focused on developing scalable generative AI methods for protein ensemble structure and dynamics modeling.

More broadly, I am interested in combining modern machine learning—particularly generative models—with physics-based modeling to better understand, simulate, and design biomolecular systems.

Research interests

• Generative machine learning for biomolecular modeling, design, and drug discovery
• Theoretical and computational chemistry, with an emphasis on molecular structure, thermodynamics, and dynamics
• Computational biology, including machine learning methods for biological and biochemical systems
• Agentic AI systems for scientific modeling, data integration, and collaborative research workflows

Get in touch

You can reach me by email, or find me on Google Scholar, GitHub, and LinkedIn.