AI Security Research & Red Team Engineer

Responsibilities

• Conduct AI security and vulnerability research across Cloudflare’s products and services, focusing on AI, agents, harnesses, and large language models.
• Identify AI-related attack surfaces through rigorous testing of agentic implementations and LLM usage.
• Define requirements and implementation guidance for secure AI adoption.
• Execute full-chain red team operations targeting global infrastructure, corporate networks, and product ecosystems.
• Establish frameworks for measuring security efficacy against known tactics, techniques, and procedures (TTPs).
• Test the effectiveness of WAF, EDR, and SIEM detections.
• Partner with Blue Team, Security Incident Response, Threat Detection, and Threat Engineering teams to translate findings into defensive improvements.
• Conduct unannounced exercises, refine incident-response playbooks, test on-call rotations, and evaluate forensic tooling.
• Identify detection gaps, develop detection logic, and validate coverage against emerging TTPs.
• Provide technical leadership and mentorship while fostering ethical hacking and security collaboration.
• Translate complex exploits into risk-based narratives for leadership and help prioritize engineering resources.
• Partner with Product Engineering and SRE as a customer-zero tester of security products and processes.
• Provide empirical evidence of control effectiveness to Governance, Risk, and Compliance teams.

Requirements

• 4+ years of experience in offensive security, application security, or a related field.
• Deep knowledge of AI, coding agents, LLMs, prompt engineering, AI-related attack vectors such as prompt injection and jailbreaking, and agentic concepts.
• Strong background in manual penetration testing, exploit development, or cloud security across AWS, Google Cloud, or bare-metal environments.
• Experience using the MITRE ATT&CK framework to map coverage and identify defensive telemetry gaps.
• Ability to explain complex exploits, including zero-day vulnerabilities, to both technical and non-technical stakeholders.
• Knowledge of automated breach and attack simulation tools and custom frameworks for payload delivery and command-and-control infrastructure.

Compensation and Benefits

• New York-based hires: estimated annual salary of $166,000–$208,000.
• Compensation may be adjusted depending on work location.
• Eligible to participate in Cloudflare’s equity plan.