I’m an AI safety researcher currently based in Sunnyvale, California, working to make advanced AI systems more transparent, controllable, and aligned with human values. My PhD research focused on mapping deep neural networks to the human brain, exploring how techniques and insights can transfer between deep learning and neuroscience. Now, my work is centered on AI safety—understanding and shaping the mechanisms, capabilities, and goals of advanced AI models.

Outside of this work, I enjoy music, film, 3D printing, and messing around with brain-computer interfaces. I’m also interested in broader questions about the interaction between society, technology, and values—how the systems we build shape us, and how we can best shape them in return.

Feel free to check out my CV or LinkedIn for more info about my background!

Thanks for checking out my site!