Research Profile
Computational Materials & Multiscale Modeling
I develop computational methods for materials and process systems by combining scientific computing,
physics-informed machine learning, and multiscale simulation. My work emphasizes transferable models,
robust algorithms, and clear physical interpretability.
Current RoleAlgorithm Developer, Applied Materials
Prior Academic RolePostdoctoral Researcher, Stanford
Core DomainsComputational Mechanics · Deep Learning · Process Optimization
MethodsMD, stochastic processes, ML force fields
Focus Areas
- Generalizable force-field modeling and transferability assessment.
- Network-physics driven understanding of polymer mechanics and failure.
- Simulation-to-experiment methods for X-ray and process-relevant observables.
- Algorithmic workflows for scale-up and robust deployment.
- Uncertainty-aware modeling for process optimization.
Education
- Ph.D., Mechanical Engineering
Stanford University — Dissertation
- M.Tech, Mechanical Engineering (Product Design)
IIT Madras — Master's Thesis
- B.Tech, Mechanical Engineering
IIT Madras
Computational Tools & Open Source
Computational X-ray Photon Correlation Spectroscopy workflows from molecular simulation trajectories.
Testbed to benchmark and generalize machine-learned force fields across polymer systems.
Algorithms for shortest-path statistics in branched polymer networks and complex topologies.
Simulation-ready preparation and initialization of polymer network structures.
