Kiran Vaddi, Ph.D.

I am a Postdoctoral Scholar in the Department of Chemical Engineering at the University of Washington, Seattle, and a UW Data Science Postdoctoral Fellow affiliated with the eScience Institute. As part of my involvement with the data science community, I co-chaired the eScience Institute’s weekly postdoc seminar series (2021–2022).

My research lies at the intersection of machine learning and materials science, with a focus on building autonomous experimentation workflows for materials discovery and design. Broadly, I develop models and representations that bridge physical insight and data-driven methods to accelerate the discovery of soft materials and nanostructures. My Ph.D. in Materials Science and Engineering (University at Buffalo, SUNY) focused on developing physics-based and data-driven models for material optimization and structure–property mapping. I received my bachelor’s and master’s degrees in Mechanical Engineering from the Indian Institute of Technology Madras, with a specialization in thermal engineering.

Research Interests

My core research interest is in learning interpretable representations for data-efficient scientific discovery, especially in settings where experimental data is expensive or sparse. I work on developing differentiable, geometry-inspired models that integrate active learning and reinforcement learning for autonomous experiment design. I am particularly interested in representations grounded in topology and differential geometry to make scientific workflows both computationally efficient and physically meaningful.

Beyond Research

Outside the lab, I’m a passionate follower of cricket and have been watching, analyzing, and writing about the game for over two decades. I also enjoy Formula 1—my weekends are often booked during the race season. I dabble in music production and play a bit of keyboard, with musical tastes ranging from A. R. Rahman to twenty one pilots and Yanni.