Hey, I'm Aditya. I studied Statistics and Data Science at UC Berkeley and currently work as an AI engineer. On the side, I'm pursuing a deep interest in mechanistic interpretability, the field trying to reverse-engineer what's actually happening inside large neural networks.

I'm drawn to the foundational questions: how do neural networks represent information, and can we develop rigorous tools to verify our answers? I think getting this right matters for AI safety in ways that go deeper and are currently underemphasized.

When I'm not coding or buried in research papers, I'm training in Muay Thai or cheering for Real Madrid. Hala Madrid.

I'm also exploring writing in my free time, most of it is still unpublished, but I'm enjoying the process because it helps me organize my thoughts and reflect more deeply.

Want to explore more? Check out my interactive Professional page to dive deeper into my projects and journey!