Artificial Intelligence (AI) Offensive Security Analyst
$31,200–$31,200 year
HybridBudapest, Budapest, Hungary
Job Summary
Design and execute penetration tests, vulnerability assessments, and Red Team adversarial evaluations against Citi's AI applications, including GenAI, agentic systems, and LLM-backed products. Leverage AI-powered tools to accelerate reconnaissance, automate validation, and expand coverage across the application portfolio. Develop test cases for attack classes such as prompt injection, retrieval poisoning, and tool misuse while embedding security checks into the development lifecycle. Collaborate with engineering teams to define standards for deploying, monitoring, and governing agentic AI at enterprise scale. Triage findings and communicate risk clearly to technical and non-technical audiences as adversaries increasingly use AI to exploit vulnerabilities faster than traditional detection methods.
Required Qualifications
- 5-7+ years of experience for Assistant Vice President level
- 8-10+ years of experience for Vice President level
- 10+ years of experience for Senior Vice President level
- Bachelor's degree in Computer Science, Information Security, Engineering, or equivalent practical experience
- Master's degree preferred
- Practical experience running penetration tests or vulnerability assessments against web applications, APIs, or mobile applications
- Red Team experience running adversary simulations as an operator
- Familiarity with common security testing tools: Burp Suite, nuclei, nmap, or similar
- Working knowledge of OWASP Top 10
- At least some exposure to OWASP LLM Top 10 or MITRE ATLAS
- Ability to triage findings and communicate risk clearly to technical and non-technical audience
- Hands-on experience using LLM tools in a meaningful way, whether for security testing, security research, or your own workflows
- Enough understanding of how LLMs work (context windows, tool use, RAG, agentic chaining) to reason about where they can go wrong
- Familiarity with AI testing tools or frameworks, even from personal research or experimentation
- Can write clearly: test plans, findings reports, risk summaries
- Curious about the security implications of AI systems, not just the hype around them
- Comfortable working on problems that don't have a playbook yet
Desired Qualifications
- Experience testing AI applications and agents
- Experience with GenAI applications, agentic systems, and LLM-backed products
- Knowledge of prompt injection, indirect injection, retrieval poisoning, tool misuse, sensitive data extraction, unsafe delegation
- Experience using AI to work better (AI-assisted testing)
- Experience embedding security into development
- Experience building tools from scratch
- Experience operating in an environment where the right approach isn't always obvious yet
- Experience with Garak, PyRIT, PromptBench, Inspect AI, or equivalent
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.