Siddarth Achar

RESEARCH:

Siddarth Achar is working on designing molecular probes for detecting toxic per- and polyfluoroalkyl substances (PFAS), persistent “forever chemicals” that contaminate drinking water. These compounds pose major risks to human health, yet current detection methods are costly, complex, or insufficiently sensitive and selective in real water systems. He is developing a Bayesian optimization–driven computational strategy that integrates statistical mechanics, molecular dynamics simulations, and generative AI to rapidly discover functionalized cyclodextrin probes with enhanced binding affinity and selectivity toward PFAS. At the University of Chicago, Siddarth is interested in advancing the fundamentals of statistical mechanics, probabilistic modeling, molecular enhanced sampling, manifold learning, and dimensionality reduction, with the goal of enabling portable and cost-effective detection technologies for environmental contaminants.

BIO:

Siddarth Achar joined the University of Chicago in 2025 as a Schmidt AI in Science Fellow, working jointly with Professors Andrew Ferguson and Junhong Chen. He received his Ph.D. in Computational Modeling and Simulation from the University of Pittsburgh under the supervision of Professor J. Karl Johnson, where he developed machine learning–based interatomic potentials and active learning frameworks to accelerate quantum-mechanical simulations of chemical reactions and materials. During his Ph.D., Siddarth applied ML-driven force fields to study proton-conducting membranes, gas adsorption in metal–organic frameworks, and reactive processes in catalytic and electronic materials, leading to methodological advances such as algorithms for charge density prediction and automated chemical reaction exploration. Prior to his Ph.D., Siddarth earned an M.S. in Chemical Engineering from Carnegie Mellon University, where he worked on computational chemical kinetics under the supervision of Professor John Kitchin.