AI Security Architect & Red Team Engineer

Triwill Group; United States; Hybrid; USD 166,000 - 208,000; Full time

Benefits offered by this job

Equity plan

Job summary

Cloudflare is seeking a highly skilled AI Security Research & Red Team engineer to join our Red Team within the Security Threat Detection, Response and Emulation organization. Drive security research, exercises, and attacker emulations to improve Cloudflare’s security posture focusing on AI, Agents, harnesses and LLMs.

You will mentor teams, lead adversary simulations, and translate complex exploits into risk-based narratives for leadership while collaborating with SIRT, threat engineering, and

Qualifications

• 4+ years in offensive security or related field.
• Deep knowledge of AI, LLMs, prompt engineering and AI attack vectors.
• Strong background in manual pentesting, exploit development or cloud security.
• Experience mapping with MITRE ATT&CK framework and communicating findings.

Responsibilities

• Lead AI security research and red team exercises across Cloudflare products.
• Test AI-related attack surfaces and define requirements for defenses.
• Perform adversary simulations targeting global infrastructure and products.
• Develop and validate detections for WAF, EDR, and SIEM.
• Mentor teams and translate findings into executive risk narratives.

Skills

AI Security

Red Team

Penetration Testing

MITRE ATT&CK

C2 Frameworks

Tools

BAS Tools

Cloud Security

AWS/GCP

Job description

Cloudflare is seeking a highly skilled AI Security Research & Red Team engineer to join our Red Team within the Security Threat Detection, Response and Emulation organization. Drive security research, exercises, and attacker emulations to improve Cloudflare’s security posture focusing on AI, Agents, harnesses and LLMs.

You will mentor teams, lead adversary simulations, and translate complex exploits into risk-based narratives for leadership while collaborating with SIRT, threat engineering, and