Principal AI Red Team Operator

Verizon•Cary, NC

7d•Hybrid

About The Position

The Verizon Cyber Security (VCS) organization enables the business by protecting assets and information across Verizon networks, infrastructure, and applications. VCS integrates cybersecurity governance, policies, technologies, and operations across Verizon, working to embed security into the design and lifecycle of technology systems. Reporting into the AI Security Operations Manager, the Principal AI Red Team Operator serves as the technical subject matter expert responsible for planning and executing end-to-end adversarial assessments on AI/ML systems. Beyond assessment execution and findings delivery, a critical component of this role is program maturation. You will lead the development of testing frameworks, playbooks, toolsets, and metrics that scale and elevate Verizon’s AI Red Teaming capability.

Requirements

Bachelor's degree or four or more years of relevant work experience.
Six or more years of relevant work experience required, demonstrated through one or a combination of job-related work experience, military experience, or specialized training or education (non-collegiate).
Experience conducting AI evaluations or developing AI Safety/Security systems.
Experience using adversarial prompting strategies (role play, DAN, etc.) to compromise enterprise AI systems.
Experience using other than prompt strategies to compromise AI systems (data poisoning, embedding inversion, etc.).

Nice To Haves

Strong understanding of AI model architectures and development.
Strong understanding of cybersecurity principles and practices.
Excellent communication and interpersonal skills.
Ability to work independently and as part of a team.
Experience in traditional web application testing.
Experience using local LLMs for prototyping and experimentation with GenAI (e.g., Ollama, LlamaFiles).
Experience in training and educating others on Generative AI tools.
Knowledge of programming languages such as Python.
Experience with cloud computing platforms such as GCP, AWS, or Azure.
Demonstrated continual learning around the field of Artificial Intelligence.

Responsibilities

Mature & Scale the Program: Build, refine, and operationalize AI red team frameworks, playbooks, and automated testing tools aligned with industry standards (e.g., MITRE ATLAS, OWASP).
Execute AI Red Teaming: Plan and conduct complex manual and automated adversarial assessments on enterprise AI systems (LLMs, RAG architectures, agents) targeting prompt injection, data poisoning, and model exploitation.
Report & Consult: Present findings and risk insights to both technical engineering teams and senior leadership, providing actionable remediation guidance to secure the AI lifecycle.
Research Emerging Threats: Track evolving GenAI vulnerabilities, experiment with novel attack vectors, and continuously enhance testing capabilities to stay ahead of adversaries.