Artificial Intelligence (AI) Offensive Security Analyst

Citi•Jersey City, NJ
•$87,280 - $212,160

About The Position

Citi’s Offensive Security and Vulnerability Management (OSVM) team is hiring an operational security practitioner to conduct penetration tests, vulnerability assessments, and Red Team adversarial evaluations across Citi’s application portfolio. The role focuses on testing AI systems as targets and using AI-powered tools to make security testing faster and more effective. The analyst will help build tools from scratch, understand their capabilities and limitations, and work in an evolving problem space without established playbooks. The position involves assessing generative AI applications, agentic systems, and LLM-backed products for threats that extend beyond standard web application testing, including prompt injection, indirect injection, retrieval poisoning, tool misuse, sensitive data extraction, and unsafe delegation. It also includes applying AI-assisted testing to improve coverage, reconnaissance, and validation, and collaborating with development teams and security engineers to integrate security assessments into development processes. The role is part of Citi’s OSVM organization, which integrates an attacker’s mindset across the technology lifecycle to safeguard Citi’s clients, partners, and business sectors. Multiple openings are available at Assistant Vice President, Vice President, and Senior Vice President levels, with scope ranging from autonomous ownership of workstreams to setting technical direction and influencing the firm’s approach to AI security. Location and compensation packages may be flexible and commensurate with experience and qualifications. Other job-related duties may be assigned as required.

Requirements

  • Practical experience conducting penetration tests or vulnerability assessments against web applications, APIs, or mobile applications, or Red Team experience running adversary simulations as an operator.
  • Familiarity with common security testing tools such as Burp Suite, nuclei, and nmap, or similar tools.
  • Working knowledge of the OWASP Top 10 and some exposure to the OWASP LLM Top 10 or MITRE ATLAS.
  • Ability to triage findings and communicate risk clearly to technical and non-technical audiences.
  • Hands-on experience using LLM tools in a meaningful way for security testing, security research, or personal workflows.
  • Sufficient understanding of how LLMs work—including context windows, tool use, RAG, and agentic chaining—to reason about their failure modes.
  • Comfort working on problems without established playbooks.
  • Ability to write clearly, including test plans, findings reports, and risk summaries.
  • Curiosity about the security implications of AI systems.
  • Bachelor’s degree in Computer Science, Information Security, Engineering, or equivalent practical experience.
  • Assistant Vice President level: 5–7+ years of experience.
  • Vice President level: 8–10+ years of experience.
  • Senior Vice President level: 10+ years of experience.

Nice To Haves

  • Master’s degree.
  • Familiarity with AI testing tools or frameworks such as Garak, PyRIT, PromptBench, Inspect AI, or equivalent, including through personal research or experimentation.

Responsibilities

  • Run penetration tests, vulnerability assessments, and Red Team adversarial evaluations across Citi’s application portfolio.
  • Design and execute security test cases for generative AI applications, agentic systems, and LLM-backed products, including testing for prompt injection, indirect injection, retrieval poisoning, tool misuse, sensitive data extraction, and unsafe delegation.
  • Use AI capabilities to broaden testing coverage, accelerate reconnaissance, and automate validation of common vulnerability classes.
  • Help build AI-powered security testing tools and support their adoption across the broader team.
  • Work with development teams and security engineers to integrate AI application assessments into the development process.
  • Triage security findings and communicate risks clearly to technical and non-technical audiences.
  • Depending on level, own workstreams end-to-end, define technical approaches and architectural decisions, mentor others, or set technical direction for AI security.

Benefits

  • Medical coverage
  • Dental coverage
  • Vision coverage
  • 401(k)
  • Life insurance
  • Accident insurance
  • Disability insurance
  • Wellness programs
  • Paid vacation
  • Paid sick leave
  • Paid holidays
  • Eligible employees may receive discretionary and formulaic incentive and retention awards.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service