Services
Under Construction
This page is being built. In the meantime, here's what I offer.
AI Red Teaming
Systematic adversarial testing of LLM applications, RAG pipelines, and agentic systems using the AATMF methodology.
Vulnerability Research
Targeted security assessments of web applications, WordPress plugins, and cloud infrastructure. 10 CVEs and counting.
AI Safety Consulting
Threat modeling, guardrail evaluation, and defense architecture for organizations deploying LLM-powered products.
Speaking & Training
Conference talks, workshops, and team training on adversarial AI, prompt injection defense, and offensive security.