AI Security Resume
AI Security practitioner combining professional application-security experience with graduate research in adaptive LLM defense -- measured prompt-injection and data-leakage mitigation, red-team methodology, and layered defense-in-depth architecture for AI-enabled systems.
Key strengths
- LLM red-teaming and adversarial prompt-injection evaluation (Promptfoo, Garak, PyRIT)
- Adaptive, risk-based defense routing -- Moving Target Defense research
- Context isolation, input risk inspection, and output redaction for LLM applications
- Canary-based data-leak detection methodology
- Defense-in-depth architecture design for LLM-enabled systems
- Test-driven security evaluation -- reproducible adversarial test sets, measured disclosure rates
- Identity/session-based authorization design closing IDOR-style AI data-leakage vectors
Supporting evidence
Have a specific role in mind?
Paste a job description to map its requirements against evidence from my experience, research and projects.
Analyze My Fit for This Role →Alternate resumes
Last updated: August 2026