I'm pursuing a double degree in Mathematics and Computer Science at the Universidad Complutense de Madrid. I research neural networks at their deepest level: from gradient dynamics to low-level optimization.

I specialize in Mechanistic Interpretability — reverse-engineering how networks represent and process information. Rather than treating models as black boxes, I decompose their circuits to understand why they work.

My mission: make AI systems transparent through rigorous mathematical analysis and low-level engineering.