Artificial Intelligence Security Specialist USA

Citi•Tampa, FL

1d•Onsite

About The Position

Citi, a leading global bank with extensive operations worldwide, is seeking an Artificial Intelligence Security Specialist to join its Chief Information Security Office (CISO). This role is crucial for ensuring the safety of Citi's clients, revenue, employees, and proprietary data by managing information security as an end-to-end program. The CISO team is at the forefront of integrating AI and cybersecurity, tackling novel problems that lack established playbooks. This includes developing AI-driven vulnerability management, defining security architecture for AI deployment, securing AI agents that can mimic insider threats, and performing real security engineering. The position offers a unique opportunity to work on cutting-edge AI security challenges at an enterprise scale, with a focus on building and operating production systems rather than just prototypes. Citi has already deployed AI tools to over 180,000 employees and equipped 30,000 developers with AI coding assistants, highlighting the significant scale and impact of this role.

Requirements

Depth in at least one of the following areas: AI/ML engineering, offensive security, detection engineering, software engineering, or security research.
Genuine curiosity about the intersection of AI and cybersecurity.
Hands-on LLM API experience (context management, tool use, evaluation, failure modes).
Experience with agentic systems design.
Understanding of AI safety at the infrastructure level.
Vulnerability research, exploit development, or pen testing experience.
Detection engineering for novel attack patterns.
Threat modeling (STRIDE, ATT&CK).
Security architecture experience.
Experience building and operating production systems.
Strong Python and/or systems programming skills.
Ability to digest dense technical research and translate it into actionable security recommendations.
Mindset of engineering solutions to problems rather than purchasing tools.
Genuinely curious, comfortable with ambiguity, biased toward building, and able to work across disciplines.

Nice To Haves

Comfortable reading disassembly or tracing through kernel code.
Published research, conference talks, or open-source contributions.
Master’s degree preferred.

Responsibilities

Develop and implement AI-driven vulnerability management solutions, focusing on triage, verification, and remediation.
Define and establish security architecture standards and evaluation frameworks for the deployment, monitoring, and governance of agentic AI.
Design and implement containment architectures and runtime controls to safely operate AI agents with insider threat-like capabilities at an enterprise scale.
Engage in real security engineering, understanding code, architecture, and threats to develop solutions.
Participate in AI-assisted penetration testing and automated exploit validation.
Define how the bank deploys AI safely, including security architecture and assurance for new implementations.
Build next-generation AI-powered tools for CISO colleagues.
Test new AI models at the cutting edge of creation and influence their development.
Own and maintain AI products used by CISO in production, ensuring reliability and rapid evolution.
Develop and implement security assurance, cyber security operations, governance, and controls for AI products.
Enhance detection, triage, and response capabilities for a landscape where adversaries use AI to exploit vulnerabilities rapidly.
Develop behavioral analytics for AI agents and create playbooks for AI-originated attack scenarios.