AI Red Team Security Engineer
Ethos Lifeabout 2 hours ago
Remote, United StatesSenior / Staff+
H1B Sponsor
Base Salary
$152k - $269k/yr
Responsibilities
- Design and execute adversarial attacks against LLM-powered products.
- Test RAG pipelines for data exfiltration and unauthorized knowledge extraction.
- Assess AI agent systems for unsafe tool-use and privilege escalation.
- Conduct model extraction and adversarial example attacks against ML models.
- Evaluate AI guardrails and content moderation layers for bypass techniques.
- Perform full-scope penetration tests across various platforms.
- Conduct red team exercises simulating advanced persistent threat actors.
- Exploit vulnerabilities across the OWASP Top 10 and beyond.
- Perform social engineering and phishing simulations.
- Conduct cloud and Kubernetes security assessments.
- Leverage AI models to accelerate vulnerability discovery and exploit development.
- Build or adapt AI-powered tools for red team engagements.
- Stay current with adversarial AI research and apply findings to red team techniques.
- Automate repetitive testing tasks using AI.
Requirements
- 7+ years of hands-on penetration testing and offensive security experience.
- Demonstrated experience testing AI/ML systems and LLM-powered products.
- Experience conducting red team engagements.
- Proficiency in scripting and tool development.
- Strong understanding of authentication protocols and common flaws.
- Familiarity with cloud security architectures and misconfigurations.
- Working knowledge of Docker/Kubernetes and container security.
- Understanding of LLM architectures and their attack surfaces.
- Familiarity with OWASP LLM Top 10.
- Practical experience with prompt injection and jailbreak techniques.
- Ability to use LLMs as force-multipliers in red team workflows.