AI Security Research & Red Team Engineer
Core
Conduct offensive security research and red team operations specifically targeting AI, agents, and LLMs to protect Cloudflare's infrastructure and customers.
Role type
Senior IC AI Security Research & Red Team Engineer
Builds
Security posture improvements for AI/LLM products and global infrastructure
Domain
Cybersecurity, AI Security, Offensive Security
Deliverable
production ML models | product features | dashboards & analysis | research | client delivery | infrastructure
Required skills
AI security research, agentic testing, LLM vulnerability assessment, prompt injection/jailbreaking defense, manual penetration testing, exploit development, cloud security (AWS/GCP/Bare Metal), MITRE ATT&CK framework usage, automated breach simulation (BAS), adversary simulation, technical leadership, executive risk reporting
Preferred skills
None explicitly stated
Technologies
LLMs, Coding agents, MITRE ATT&CK, BAS tools, C2 infrastructure, WAF, EDR, SIEM
Responsibilities
Identify AI-specific vulnerabilities and risks, execute full-chain red team operations, establish security efficacy testing frameworks, partner with Blue Team for defensive improvements, mentor team members, translate technical exploits for leadership, conduct unannounced exercises with SIRT, lead detection logic development
Seniority
Senior, hands-on IC with mentorship responsibilities