I work in AI security with a focus on agentic systems.

I'm a Founding AI Security Engineer at Prologis and an AI Safety Fellow at MIT AI Alignment. I have 18+ CVEs across OSS AI agent frameworks and two published empirical papers studying how deployed agents fail under adversarial conditions, including work accepted at ICML 2026.

I finished my B.S. in Cybersecurity at the University of South Florida where I won the Golden Bull Award and the Boundless Bull Award. I'll be continuing at Georgia Tech with an M.S. in Computer Science with an AI/ML specialization. I am an HTB Certified Offensive AI Expert. My background is in offensive security and cloud security through internships at Honeywell, JPMorgan, and Wells Fargo. I also competed on USF CyberHerd's red team, winning national CTF competitions.

Outside of work I box. In college I founded USF's boxing club, the largest combat sports club in school history, 1,200 members, back-to-back Outstanding Sports Club of the Year.

Shoot me an email at gamagey@usf.edu for research collaboration on AI safety/security.