About Me

I am a recent graduate of UC San Diego getting a bachellors degree in Computational Physics and a minor in Mathematics. I have a strong interest in the intersection of physics/mathematics and machine learning. My goal is to develop efficient machine learning models rooted in the underlying physical and mathematical principles the govern the world and their task.

I am currently taking a gap year in Zurich Switzerland, studying Datascience at ETH Zurich before starting my PhD the following year at Yale University in Elecrical & Computer Engineering. I will be focusing on creating new mathematically driven ML models and applying them on impactful fields such as genomics.

I have been fortunate to have worked with many insigthful and insipiring mentors. Over the past few years I have worked with Professor Javier Duarte and Nhan Tran, focusing on optimizing neural networks for nanosecond timescales using FPGAs. Our work involves creating a Neural Architecture Codesign (NAC) pipeline that automates the discovery and optimization of efficient machine learning models for scientific and engineering applications. More recently, we have worked on a surrogate model to predict FPGA latency times for ML models synthesized to FPGA chips.

I have also had the opportunity to work with Professor Lesya Shchutska at EPFL on demonstrating the existence of heavy neutral leptons using machine learning techniques, and with Professor Yiwen Chu at ETH Zurich on designing a vibration damping system for a cryo fridge. These experiences have reinforced my belief in the power of incorporating fundamental principles to create better solutions.

My philosophy is that by understanding and leveraging the underlying physics and mathematics, we can develop machine learning models that provide meaningful insights and push the boundaries of scientific discovery. I am excited to continue pursuing this approach in my future research endeavors.