AI Penetration Tester

This is a fully remote position, open to applicants in Arizona, +3 more states.

📋 Description

• Carry out security evaluations of AI systems, large language models (LLMs), AI agents, and machine learning applications.

• Conduct adversarial testing which includes prompt injection, jailbreaks, model manipulation, and abuse-case testing.

• Implement security testing for applications, APIs, and cloud environments that support AI-enabled solutions.

• Create repeatable methodologies, tools, and automation for AI security testing.

• Collaborate with development and engineering teams to verify and address identified issues.

• Generate technical reports and executive summaries that communicate risks and suggest recommendations.

• Investigate emerging threats and attack techniques related to AI.

• Assist with red team exercises that involve AI-enabled attack scenarios.

⛳️ Requirements

• Generally, 7+ years of pertinent experience.

• A post-secondary degree in Information Security, Computer Science, Engineering, Information Systems, Business, or a related field.

• Multiple Information Security certifications from a recognized institution (e.g., (ISC)2, ISACA, SANS).

• Advanced experience in penetration testing across web applications, APIs, and cloud environments.

• Practical experience in assessing AI/LLM technologies, AI agents, ML models, or generative AI applications.

• Deep understanding of offensive security methodologies and adversarial attack strategies.

• Proficiency in Python scripting and development/automation of security tools.

• Familiarity with OWASP Top 10, API Security Top 10, and emerging OWASP LLM Security vulnerabilities.

• Experience in threat modeling and conducting security assessments.

• Solid understanding of authentication, authorization, identity, and cloud security principles.

🏝️ Benefits

• Health insurance.

• Tuition reimbursement.

• Accident and life insurance.

• Retirement savings plans.