AI Security Research & Red Team Engineer

What you'll do

• Perform deep-dive research to identify AI-specific vulnerabilities and risks across products and services.
• Test agentic implementations and LLM usage to identify attack surfaces and define implementation guidance.
• Execute full-chain red team operations targeting global infrastructure, corporate networks, and product ecosystems.
• Establish a framework to measure the efficacy of WAF, EDR, and SIEM detections against known TTPs.
• Partner with the Blue Team to translate red team findings into immediate defensive improvements.
• Conduct unannounced exercises for the Incident Response Team to refine playbooks and test forensic tooling.
• Develop new detection logic and validation frameworks to bridge gaps between simulation and defensive coverage.
• Translate complex technical exploits into risk-based narratives for executive leadership.

What we're looking for

• 4+ years of experience in offensive security, application security, or a relevant field.
• Deep knowledge of AI, coding agents, LLMs, prompt engineering, and AI-related attack vectors like prompt injection and 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 blind spots in defensive telemetry.
• Knowledge of automated breach and attack simulation (BAS) tools and custom-built frameworks for payload delivery and C2 infrastructure.
• Ability to explain complex 0-day exploits to non-technical stakeholders while maintaining technical depth for engineering teams.
• Export control laws, including the U.S. Export Administration Regulations.