Karthik Viswanathan

I recently completed my PhD at the University of Amsterdam in the Institute of Physics on geometric and statistical physics-based methods for interpretability of large language models. Prior to this, I was working on analyzing the large-scale structure of the universe using topological data analysis.

My interdisciplinary journey began with competitive programming, progressed through developing machine learning models as a surveillance analyst at Goldman Sachs, and continued with my master’s in theoretical physics. This cross-domain experience has enabled me to transition smoothly across disciplines and contribute to both practical implementations and theoretical research.