Karina Nguyen

My research in machine learning aims to apply the state-of-art in open-source intelligence and reliable interfaces for AI deployment. Exploring robustness of vision models led me to work on a novel tool for anticipating AI model's failures and invent new investigative workflows.

I am supervised by Joseph Gonzalez, Trevor Darrell, Lisa Dunlap, and Neerja Thakkar at Berkeley AI Research. I am also co-leading the Interactive Reading Group at Cohere for AI.


My work in visual open-source intelligence & human rights research involved data collection, evidence verification, satellite analysis, 3D reconstructions, legal submissions, interactive visualizations, investigative tools, and applied remote sensing.

Past Work

As a product designer who codes I built products, internal tools, and new features with teams at Primer.ai, Dropbox, Square, and the New York Times.

Say Hi!

If you are interested in collaborating, chatting, or sharing your ideas reach me at karinanguyen@berkeley.edu or shoot me a message on Twitter:) I do freelance in OSINT consulting, design, and web development. You can also subscribe to my newsletter.