Find Unlimited Emails.For Free.
Discover prospects, find their business emails, and build your pipeline with Unifers.
Start for FreeBrian Guzman
Ai Red Team @Straiker
Signup · Get unlimited contacts
WORK HISTORY
Ai Red Team @Straiker
Саннивейл, CA, US
Conducted adversarial testing of AI/LLM systems to identify vulnerabilities in safety and security. • Designed and executed attack scenarios, including prompt injections and guardrail bypasses, to assess model robustness. • Evaluated model outputs for harmful content generation and sensitive data disclosure, contributing to ongoing research.
EDUCATION
Instituto Tecnológico de Mérida
Ingeniería, Ingeniería de sistemas
ABOUT BRIAN GUZMAN
Currently pursuing a degree in Ingeniería de Sistemas at Instituto Tecnológico de Mérida, expected to graduate in December 2026. My academic journey has been complemented by hands-on experience in cybersecurity and artificial intelligence, with a focus on adversarial testing and red teaming techniques. At Straiker, I contribute to the identification of vulnerabilities in AI/LLM systems through adversarial testing, designing attack scenarios, and evaluating model outputs for potential risks. My work reflects a commitment to advancing the safety and security of AI systems while growing my expertise in red team operations and cybersecurity.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.