Director of AI Security Research
Core
Lead and scale AI security research, red teaming, and guardrails engineering to secure LLMs, GenAI, and agentic AI systems.
Role type
Director of AI Security Research (hands-on IC with team leadership)
Builds
Automated AI red-teaming platforms (RLGym), guardrails, monitoring, and secure AI deployment practices
Domain
AI/ML Security, Generative AI, Agentic AI
Deliverable
production ML models
Required skills
AI red teaming, adversarial ML, LLM security, GenAI security, agentic AI security, team scaling, strategy definition, automated testing platform development, OWASP AI Security frameworks, MITRE ATLAS, NIST AI RMF, secure architecture design
Preferred skills
Published research, conference speaking (Black Hat, DEF CON), AI security product building, LangChain, AutoGen, MCP, A2A
Technologies
LangChain, AutoGen, MCP, A2A, RLGym
Responsibilities
Lead and scale teams across AI security research and adversarial research; Define AI security research strategy and roadmap; Conduct advanced adversarial testing of LLMs and agents; Research attack techniques including prompt injection and jailbreaks; Build automated AI red-teaming platforms; Partner with product and engineering to build guardrails and secure deployment practices; Represent the company through research and thought leadership
Seniority
Director, strategic leadership with hands-on technical execution
