AI Red Team Security Engineer

Ethos

AI Red Team Engineer for Ethos Life simulating adversarial attacks across applications and AI systems. Leveraging AI tools while conducting penetration tests and red team engagements.

Posted 6/16/2026full-timeRemote • 🇺🇸 United StatesSeniorLead💰 $152,000 - $269,000 per yearWebsite

Tech Stack

Tools & technologies

CloudDockerKubernetes

About the role

Key responsibilities & impact

Simulate real-world adversaries and exploit vulnerabilities across applications and AI/ML systems
Design and execute adversarial attacks against LLM-powered products
Test RAG pipelines for data exfiltration and unauthorized knowledge extraction
Conduct penetration tests across various environments
Perform red team exercises simulating APT actors
Use AI models and tools to accelerate vulnerability discovery and exploit development

Requirements

What you’ll need

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
Experience conducting red team engagements
Scripting and tool development
Strong understanding of authentication protocols and common implementation flaws
Familiarity with cloud security architectures and common misconfigurations
Working knowledge of Docker/Kubernetes and container security
Understanding of LLM architectures and how they relate to attack surfaces.
Familiarity with OWASP LLM Top 10
Practical experience with prompt injection and jailbreak techniques against LLMs
Ability to use LLMs as force-multipliers in red team workflows.

Benefits

Comp & perks

Health insurance
401(k) matching
Professional development opportunities
Paid time off
Flexible work arrangements

ATS Keywords

✓ Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

penetration testingoffensive securityadversarial attacksvulnerability discoveryexploit developmentscriptingtool developmentauthentication protocolscontainer securityprompt injection