Senior Red Team AI Security Engineer

Sourced from jobs.bilh.org

A senior red team security engineer role focused on adversarially testing and hardening generative AI systems at Beth Israel Lahey Health. The position leads red team operations simulating prompt injection, data poisoning, model inversion, and evasion attacks against AI/ML models. You will drive AI red teaming best practices, ethical alignment, and collaborate with AI researchers and blue teams to strengthen defenses.

• Lead and execute red team operations against AI/ML systems, simulating prompt injection, data poisoning, model inversion, and evasion attacks
• Evaluate AI systems for ethical risks, bias, fairness, and harmful content generation in collaboration with trust and safety teams
• Develop custom tools, exploits, and automated testing frameworks for AI security assessments
• Research emerging AI threats and integrate AI/ML tools into red team methodologies
• Mentor junior engineers and lead small teams during engagements
• Collaborate with blue and purple teams to validate detections against AI-targeted attacks such as LLM jailbreaking
• Plan and execute full-lifecycle red team operations including reconnaissance, command and control, and adversary emulation

• 3–5+ years of experience in offensive security, penetration testing, or red teaming
• 1–2+ years of hands-on experience with AI/ML systems and frameworks
• Expertise with red teaming tools such as Kali Linux, Metasploit, Wireshark, and Burp Suite
• BS degree preferred
• Understanding of machine learning fundamentals and model architectures

• Certified Ethical Hacker (CEH), OSCP, OSEP, or similar offensive security certifications
• AI/ML security certifications
• Experience with AI model interpretability and automation tools
• Traditional penetration testing and red team methodologies