Artificial Intelligence (AI) Offensive Security Analyst

About the role

The AI Offensive Security Analyst will run security assessments against AI systems and use AI-powered tools to make security testing faster and more effective. The role involves testing AI applications and agents, embedding security into development, and defining technical approaches.

Responsibilities

• Test AI applications and agents, focusing on prompt injection, indirect injection, retrieval poisoning, tool misuse, sensitive data extraction, and unsafe delegation.
• Use AI to enhance security testing, such as broader coverage, faster reconnaissance, and automated validation of common vulnerability classes.
• Work with development teams to integrate security assessments into the build process.
• Design and execute test cases for AI-specific attack classes and scenarios.
• Communicate findings and risks clearly to both technical and non-technical audiences.

Requirements

• Practical experience running penetration tests or vulnerability assessments against web applications, APIs, or mobile applications.
• Familiarity with common security testing tools like Burp Suite, Nuclei, and Nmap.
• Working knowledge of OWASP Top 10 and exposure to OWASP LLM Top 10 or MITRE ATLAS.
• Experience using AI tools for security testing, research, or personal workflows.
• Understanding of how LLMs work, including context windows, tool use, RAG, and agentic chaining.
• Comfortable working on problems that don't have established playbooks.
• Ability to write clear test plans, findings reports, and risk summaries.

Qualifications

• 5-7+ years of security testing experience.
• 8-10+ years of experience for Vice President level.
• 10+ years of experience for Senior Vice President level.

Skills

• Security Testing
• AI Penetration Testing
• Artificial Intelligence (AI)
• Cybersecurity
• Large Language Models (LLMs)
• Mitre ATT&CK Framework
• OWASP Top 10
• Penetration Testing