Patrick Mendoza

Hi there, I’m Patrick. I’m a 4th year at UC Berkeley studying EECS and Applied Math. My research focuses within the realm of alignment and interpretability, with a particular interest in AI Safety.

Currently, I’m an undergraduate researcher in Berkeley’s Artifical Intelligence Resarch (BAIR) Lab working on speech-language models under Cheol Jun Cho and Professor Gopala Anumanchipalli and with David Wagner’s Research Group, in safety alignment under Zhanhao Hu and Professors David Wagner and Raluca Popa.

Outside of school, I am a huge soccer fan, I love playing video games, and I have 4 cats!