Senior AI-Driven Red Team Threat Specialist

Bank of America; Denver (CO); On-site; USD 160,000 - 205,000; Full time

Benefits offered by this job

Benefits eligible

In-office culture

Job summary

Bank of America is seeking an experienced security professional to lead AI security testing, advise on vulnerabilities, and communicate risk to stakeholders. The role focuses on offensive security testing across diverse platforms, including AI-enabled systems.

You will collaborate with Global Information Security, risk partners, and executive leadership to identify, communicate, and remediate risk. Strong technical and communication skills are essential.

Qualifications

• Lead AI security testing engagements, including scope and guardrails.
• Covert red team operations emulating advanced threat actors.
• Understand AI/LLM security concepts and attack techniques (prompt injection, etc.).
• Understand how generative AI may be used for reconnaissance and social engineering.
• Evaluate AI-enabled systems from adversarial perspectives and identify attack paths.
• Experience with red-teaming tools (Metasploit, Burp Suite, Cobalt Strike).
• Develop implants and evasion techniques for security controls.
• Solid understanding of networks, Windows/Linux/macOS, AD, and MITRE ATT&CK.

Responsibilities

• Perform vulnerability research and testing across platforms.
• Document risk and business impact in clear reports.
• Assist business units with vulnerability remediation questions.
• Explain technical findings to non-technical audiences.
• Collaborate with Global Information Security and leadership to remediate risks.

Skills

AI security testing

Threat analysis

Advisory

Technical documentation

Collaboration

Presentation skills

Mentoring

Scenario planning

Test engineering

Controls management

Information systems management

Tools

Metasploit

Burp Suite

Cobalt Strike

Job description

Bank of America is seeking an experienced security professional to lead AI security testing, advise on vulnerabilities, and communicate risk to stakeholders. The role focuses on offensive security testing across diverse platforms, including AI-enabled systems.

You will collaborate with Global Information Security, risk partners, and executive leadership to identify, communicate, and remediate risk. Strong technical and communication skills are essential.