AI Security Research & Red Team Engineer

Join Cloudflare as an AI Security Research & Red Team Engineer. In this critical role, you will be at the forefront of protecting the company and its customers from malicious threats. Your responsibilities will include driving security research, emulating real-world attackers, and improving Cloudflare's security posture. You will also collaborate with the Blue Team, mentor others, and report to executives. This position offers competitive pay, flexible vacation, paid parental leave, comprehensive benefits, and a supportive work environment.

• Conduire des recherches sur la sécurité, des exercices et des activités qui imitent les attaquants et les attaques du monde réel pour améliorer la posture de sécurité de Cloudflare, en mettant l'accent sur l'IA.
• Identifier les surfaces d'attaque liées à l'IA grâce à des tests rigoureux des mises en œuvre agentiques et de l'utilisation des LLM, et définir les exigences et les orientations de mise en œuvre.
• Établir un cadre rigoureux pour tester l'efficacité de la sécurité, en mesurant exactement la performance de nos détections contre les TTP connus.

• Operational Mindset: Experience using the MITRE ATT&CK framework to map coverage and identify "blind spots" in defensive telemetry
• Tooling Familiarity: Knowledge of automated breach and attack simulation (BAS) tools, as well as custom-built frameworks for payload delivery and C2 infrastructure
• Experience: 4+ years in offensive security, application security or other relevant field
• Technical Roots: A strong background in manual penetration testing, exploit development, or cloud security (AWS/GCP/Bare Metal)
• Deep knowledge: AI, Coding agents, LLMs, prompt engineering, AI-related attack vectors (e.g., prompt injection, jailbreaking), and Agentic concepts all for use in the red team but also testing Cloudflare uses
• Communication Skills: The ability to explain a complex "0-day" exploit to a non-technical stakeholder while maintaining the respect of a deep-dive engineering team