Lead AI Red Team operations targeting foundation and custom models, model deployment environments, training/evaluation/inference pipelines, and data ingestion, labeling, and governance controls
Design and execute AI-specific threat emulation aligned to real-world adversaries, misuse scenarios, and emerging attack techniques
Develop and maintain custom AI red team tooling, frameworks, and automation
Perform security research into emerging AI attack techniques, model vulnerabilities, and defensive gaps
Partner with detection, engineering, and governance teams on purple-team and control validation activities
Contribute to AI security standards, testing guidance, and program strategy
Mentor and provide technical leadership to red team engineers
Own the design, execution, and reporting of AI-focused red team operations, adversarial testing, and threat emulation exercises
Identify, validate, and communicate AI-related risks and articulate business impact
Requirements
- Bachelor's degree, or equivalent work experience
- Eight plus years of relevant experience
- Thorough understanding of applicable information security systems, policies, and procedures
- Effective communication, presentation, leadership, problem-solving, and analytical skills
- Proven collaboration and influencing skills
- Hands-on experience testing or securing AI/ML systems, including LLMs or other model classes
- Knowledge of AI threat models and attack techniques, including prompt injection, model extraction, training data poisoning, inference abuse, and hallucination exploitation
- Familiarity with AI platforms and tooling, including model APIs, orchestration frameworks, and evaluation pipelines
- Significant red team experience, including adversary emulation and multi-stage attack chains
- Proven skill developing proof-of-concept exploits and custom offensive tooling
- Strong understanding of red team and offensive AI techniques and tooling
- Expertise defeating or bypassing endpoint and AI-adjacent security controls, including EDR/XDR, API protections, and guardrails
- Experience with cloud, containerized, and AI-hosting environments
- Proficiency in one or more of Python, PowerShell, Go, C/C++, or Shell
- Ability to translate research into operational tooling
- Exceptional written and verbal communication skills
- Ability to work from a U.S. Bank location three or more days per week
- Ability to comply with U.S. Bank policies and procedures, including the Code of Ethics and Business Conduct and workplace conduct and safety policies
Core Competencies
Demonstrates expertise in AI Red Team operations, including threat emulation, model security, and risk communication. Proficient in developing custom tooling and frameworks while collaborating with cross-functional teams to enhance AI security standards.
Highest-signal resume keywords
- AI Red Team Operations
- AI Threat Models
- Adversary Emulation
- Python Programming
- Custom Offensive Tooling
ATS Optimization Keywords
Hard Skills
- AI/ML System Security
- Model Vulnerability Assessment
- Proof-of-Concept Exploits
- Red Team Techniques
- Threat Emulation
- Model APIs
- Orchestration Frameworks
- Cloud Environments
- Containerized Environments
- Endpoint Security Bypass
Soft Skills
- Effective Communication
- Leadership
- Problem-Solving
- Analytical Skills
- Collaboration
Industry Keywords
- Information Security
- AI Security Standards
- Model Deployment
- Data Governance
- Emerging Attack Techniques
Tools & Technologies
- EDR/XDR
- API Protections
- AI Platforms
- Automation Frameworks
- Evaluation Pipelines