AI Red Team Security Engineer (Cybersecurity)

TL;DR

AI Red Team Security Engineer (Cybersecurity): Simulating real-world adversaries to exploit vulnerabilities across applications, cloud infrastructure, and AI/ML systems with an accent on LLM pipelines, RAG systems, and AI-augmented attack tooling. Focus on designing adversarial attacks (prompt injection, jailbreaking), conducting full-scope penetration tests, and automating vulnerability discovery using AI.

Location: Remote (Must be based in the US)

Salary: $152,000 – $269,000

Company

Ethos is a leading life insurance technology company democratizing access to life insurance through a robust three-sided technology platform.

What you will do

• Design and execute adversarial attacks against LLM-powered products, including prompt injection, jailbreaking, and goal hijacking.
• Test RAG pipelines for data exfiltration, poisoning, and unauthorized knowledge extraction.
• Perform full-scope penetration tests across web apps, REST/GraphQL APIs, mobile apps, and cloud environments (AWS, GCP, Azure).
• Conduct red team exercises simulating advanced persistent threat (APT) actors using MITRE ATT&CK.
• Build and adapt AI-powered reconnaissance and exploitation tooling to accelerate vulnerability discovery.
• Evaluate AI guardrails, safety filters, and content moderation layers for bypass techniques.

Requirements

• 7+ years of hands-on penetration testing and offensive security experience in a professional setting.
• Demonstrated experience testing AI/ML systems, LLM-powered products, or AI APIs.
• Professional experience conducting red team engagements.
• Proficiency in scripting and tool development.
• Strong understanding of authentication protocols, cloud security architectures, and Docker/Kubernetes.
• Must be based in the US.

Nice to have

• Certifications: OSCP, OSEP, CRTO, CRTE, PNPT, CEH, GPEN, GWAPT, or equivalent.
• Contributions to open-source security tooling or published CVEs.
• Experience with adversarial ML frameworks and GenAI infrastructure.
• Background in threat modeling for AI-powered applications.

Culture & Benefits

• Competitive national base salary range.
• Comprehensive US benefits package.
• Remote work flexibility within the US.
• Commitment to a diverse, inclusive, and authentic workplace.