About Me

I'm a Computer Science student at the University of Washington's Paul G. Allen School of Computer Science & Engineering, maintaining a 4.0 GPA while pursuing research at the intersection of geometric deep learning and mechanistic interpretability.

My research focuses on understanding and improving machine learning models through geometric principles. I'm particularly interested in sparse autoencoders, equivariant neural networks, and building interpretable ML systems that respect the underlying structure of data.

Currently, I'm a Research Fellow at Algoverse AI, where I work on developing novel approaches to sparse autoencoders and building scalable ML infrastructure. My work combines theoretical insights from geometric deep learning with practical engineering to create more efficient and interpretable models.