The AI Offensive Security Analyst role at Citi focuses on conducting security assessments against AI systems while utilizing AI-powered tools to enhance security testing efficiency. This position is part of the Offensive Security and Vulnerability Management team, which is dedicated to ensuring the safety of Citi's clients and proprietary data. The role involves both testing AI systems and leveraging AI tools in security practices. Candidates will work on innovative security challenges that do not yet have established playbooks.

• 5-7+ years of experience in security testing, including penetration tests or vulnerability assessments.
• Familiarity with common security testing tools such as Burp Suite, nuclei, and nmap.
• Working knowledge of OWASP Top 10 and exposure to OWASP LLM Top 10 or MITRE ATLAS.
• Hands-on experience using LLM tools for security testing or research.
• Bachelor's degree in Computer Science, Information Security, Engineering, or equivalent practical experience.

• Conduct penetration tests and vulnerability assessments on AI applications and agents.
• Design and execute test cases for various attack classes affecting AI systems.
• Utilize AI-assisted testing to improve coverage and efficiency in security engagements.
• Collaborate with development teams to integrate security assessments into the software development lifecycle.
• Communicate findings and risks clearly to both technical and non-technical audiences.

• Citi offers a comprehensive benefits package including competitive pay, stock programs, healthcare coverage, retirement plans, paid time off, parental leave, and programs supporting employee wellbeing and professional development.