Senior Red Team AI Security Engineer

Beth Israel Lahey Health

1d•$125,000 - $160,000

About The Position

The Senior Red Team AI Security Engineer proactively tests and improves the resilience of generative AI systems against real-world threats. The role collaborates with AI researchers, product and project managers, engineers, machine learning engineers, data scientists, and security teams to assess model performance under adversarial conditions and provide actionable recommendations for strengthening defenses. The engineer leads AI-focused red team operations and evaluates AI systems for vulnerabilities, ethical risks, bias, fairness issues, and harmful content generation. The role develops tools and automated testing frameworks, researches emerging AI threats, integrates AI/ML tools into red team methodologies, mentors junior engineers, and supports incident response. It also works with blue and purple teams to validate detections and improve enterprise readiness.

Requirements

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.
Beth Israel Lahey Health requires staff to be vaccinated against influenza as a condition of employment.

Nice To Haves

Bachelor of Science degree preferred.
Preferred certifications include Certified Ethical Hacker (CEH), OSCP, OSEP, or similar offensive security certifications.
AI/ML security certifications preferred.
Understanding of machine learning fundamentals and model architectures.
Experience with AI model interpretability and automation tools.
Knowledge of traditional penetration testing and red team methodologies.

Responsibilities

Lead and execute red team operations targeting AI/ML systems, simulating attacks such as prompt injection, data poisoning, model inversion, and evasion against generative AI, computer vision, and natural language processing models.
Evaluate AI systems for ethical risks, bias, fairness issues, and harmful content generation, and collaborate with trust and safety teams to assess responsible AI compliance and mitigate societal impacts.
Develop and deploy custom tools, exploits, and automated testing frameworks for AI security assessments, including adversarial input generation and privacy-preserving attacks on federated learning environments.
Research emerging AI threats, publish findings on offensive AI techniques, and integrate AI/ML tools into red team methodologies for threat simulation and anomaly detection.
Mentor junior engineers in AI-specific red teaming, lead small teams during engagements, and collaborate with blue teams to validate detections against AI-targeted attacks such as LLM jailbreaking.
Stay current on AI security research, adversarial machine learning techniques, and ethical AI frameworks.
Work with machine learning engineers, data scientists, product managers, and AI researchers to evaluate model performance under adversarial conditions and recommend improvements to AI defenses.
Provide technical support to incident response teams, analyze vulnerabilities during investigations, and assist with corrective measures.
Collaborate with blue teams, purple teams, and broader security groups to stress-test systems, validate detection mechanisms, and improve enterprise readiness.
Plan, coordinate, and execute full-lifecycle red team operations, including reconnaissance, command and control setup, lateral movement, and adversary emulation.