Lead AI Red Team Engineer – Offensive AI Security

U.S. Bank; Earth City (MO); On-site; USD 127,000 - 149,000; Full time

Benefits offered by this job

Healthcare

Life insurance

Disability insurance

Parental leave

401(k)

Paid vacation

Holidays

Adoption assistance

Sick leave

Job summary

U.S. Bank is seeking an AI Red Team Lead Engineer to drive offensive security activities for AI/ML systems, pipelines, and integrations. Lead red team operations, design tests, and report findings to elevate risk visibility across models, data flows, and AI-enabled apps.

You will mentor red team engineers, partner with detection, governance, and engineering teams, and shape AI security standards and program strategy. This role requires working from a U.S.

Qualifications

• Bachelor's degree or equivalent work experience.
• Eight or more years of relevant experience in security or AI focus.
• Strong understanding of information security systems, policies, and procedures.
• Excellent communication, presentation, leadership, problem-solving and analytical skills.
• Proven collaboration and influencing skills.

Responsibilities

• Lead AI Red Team operations, including adversarial testing of foundation and custom models, APIs, and data pipelines.
• Design and execute AI-specific threat emulation aligned to real-world adversaries and emerging attack techniques.
• Develop and maintain custom AI red team tooling and automation to scale testing.
• Perform security research into AI attack techniques, model vulnerabilities, and defensive gaps.
• Partner with detection, governance, and engineering teams to support purple-team activities.
• Contribute to AI security standards, testing guidance, and program strategy.
• Mentor and provide technical leadership to red team engineers.

Skills

Bachelor's degree

Eight+ years

InfoSec knowledge

Leadership

Communication

Collaboration

Education

Bachelor's degree or equivalent

Tools

Python

PowerShell

Go

C/C++

Shell

Job description

U.S. Bank is seeking an AI Red Team Lead Engineer to drive offensive security activities for AI/ML systems, pipelines, and integrations. Lead red team operations, design tests, and report findings to elevate risk visibility across models, data flows, and AI-enabled apps.

You will mentor red team engineers, partner with detection, governance, and engineering teams, and shape AI security standards and program strategy. This role requires working from a U.S.