Software security is the core reason I became a researcher. To me, a vulnerability is more than a technical failure; it is a symptom of the complex, living organism that is human-technology interaction. My journey to understand this has spanned over 10 years, taking me from architecting financial backends serving millions of users to defending the world’s largest AI infrastructures.

I have explored the security landscape from every angle - from investigating why developers write vulnerable code during my PhD to fine-tuning GPT-2 for disinformation research at FireEye. Now, as an Applied Scientist and Security Researcher at organizations like Google and Iru, I focus on the pressing reality of the AI era: while LLMs and autonomous agents have exponentially expanded the attack surface, the bar to compromise these systems has dropped. Currently, I am focused on solving the ‘blind spots’ in generative AI and welcome new challenges in building robust, secure AI ecosystems.

Download my resumé.