AI Security Research & Red Team Engineer
$166k - $208k • Remote • Hybrid
Posted 8d ago
Job Location
Hybrid
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Engineer
About the job
We are seeking a highly skilled AI Security Research & Red Team Engineer to join our Security Threat Detection, Response and Emulation organization. This critical role will be at the forefront of protecting our company and customers from malicious threats. You will be responsible for driving security research, exercises, and activities that emulate real-world attackers and attacks to improve Cloudflare’s security posture, with a specific focus on AI, Agents, harnesses, and LLMs. You will act as a technical leader, fostering a culture of curiosity and ethical hacking, and translating complex technical exploits into risk-based narratives for leadership.
Responsibilities
- Conduct AI security and vulnerability research, identifying AI-specific and general vulnerabilities across Cloudflare’s products and services.
- Perform rigorous testing of agentic implementations and LLM usage to identify AI-related attack surfaces.
- Execute full-chain red team operations targeting Cloudflare’s global infrastructure, corporate networks, and product ecosystems.
- Establish a framework for testing security efficacy of WAF, EDR, and SIEM detections against known TTPs.
- Collaborate with the Blue Team to ensure findings translate into immediate defensive improvements.
- Serve as a sparring partner for the Security Incident Response Team (SIRT) to refine playbooks and test tooling.
- Partner with Threat Detection & Threat Engineering teams to identify detection gaps and develop new detection logic.
- Provide empirical evidence of control effectiveness to bridge the gap between 'paper security' and 'technical reality' for GRC.
Requirements
- 4+ years in offensive security, application security, or a relevant field.
- Deep knowledge of AI, coding agents, LLMs, prompt engineering, and AI-related attack vectors (e.g., prompt injection, jailbreaking).
- Strong background in manual penetration testing, exploit development, or cloud security (AWS/GCP/Bare Metal).
- Experience using the MITRE ATT&CK framework to map coverage and identify defensive telemetry blind spots.
- Ability to explain complex technical exploits to non-technical stakeholders.