Professional Overview
I’m an AI Assurance Auditor specializing in AI security red teaming. I test LLM applications and AI agents for prompt injection, jailbreaks, data leakage, excessive agency and the rest of the OWASP LLM Top 10. I built AgentRedTeam, an open-source red teaming framework in Python using LangChain and AWS Bedrock. It attacks a live agent for prompt injection, excessive agency, insecure output handling and sensitive disclosure, maps findings to governance frameworks, and generates reports. It has 34 passing tests and CI on GitHub I have about 3 years of offensive security experience, including as a team lead. I also work in AI governance, because you can’t govern what you don’t technically understand. Open to freelance, contract and full-time work in AI red teaming and AI assurance.