Juliette Pluto

I’m Juliette Pluto, a Staff Software Engineer at Google DeepMind in New York City. I work on adversarial robustness for frontier AI systems—lately, mostly prompt injection: what an agent should do when the data it reads tries to give it orders. *** I started DeepMind’s first effort to defend against prompt injection. My work spans security evaluations for frontier model selection, robustness for Gemini, and practical defenses for production systems. *** Before that, I worked on trusted execution environments and privacy-preserving ML at Google in London, and helped scale N26’s web platform in Berlin. *** Read my CV for the details, say hi at j@jul.sh, or find me on GitHub and Twitter.