Principal AI Security Researcher
Core
Lead purple team simulations and conduct hands-on attacks against AI systems to identify vulnerabilities and inform security products.
Role type
Principal AI Security Researcher (IC)
Builds
Scalable AI red teaming tooling, automation, and evaluation frameworks
Domain
AI Security / Adversarial Machine Learning
Deliverable
production ML models | product features | research
Required skills
Adversarial mindset, LLM architecture understanding, agentic AI system familiarity, Python for automation, AI security framework knowledge (MITRE ATLAS, OWASP), vulnerability research, prompt injection techniques, data exfiltration methods, model attack techniques
Preferred skills
Publications in AI security, CTF participation, open-source AI red teaming contributions, executive communication
Technologies
Python, LLM APIs, orchestration frameworks, attack harnesses
Responsibilities
Design and execute purple team simulations, develop attack harnesses for prompt injection and jailbreaks, bypass guardrails and content filters, conduct data exfiltration and model extraction research, evaluate AI defense effectiveness, deliver executive briefings and technical reports, mentor team members
Seniority
Principal, technical leadership & mentorship