Global Red Team Senior AI Engineer, Vice President

Mitsubishi UFJ Financial Group•Jersey City, NJ

2d•Hybrid

About The Position

The Vice President, Global Red Team & AI Security Operations leads enterprise-wide red team and AI adversarial testing programs to emulate real-world threat actors and strengthen organizational resilience. This role oversees advanced attack execution, AI red teaming, and operator capability development, translating findings into measurable risk reduction in partnership with defensive, engineering, and governance teams.

Requirements

7+ years of experience in red team and offensive security, including leading advanced attack simulations.
Demonstrated experience planning and executing attacks that evade network, endpoint, application, and cloud controls.
Hands-on experience with AI red teaming, adversarial testing, and LLM security assessments.
Experience assessing AI-enabled applications, LLM agents, retrieval-augmented generation systems, model access controls, tool/plugin permissions, and enterprise data connectors.
Proven ability to translate highly technical attack results into executive-level risk narratives, control validation outcomes, and prioritized remediation actions.
Deep knowledge of application security vulnerabilities, exploitation techniques, and web/API workflows.
Experience developing or modifying offensive tooling (e.g., implants, loaders) and operating modern C2 frameworks.
Strong operational knowledge of Windows and Linux, including persistence and lateral movement techniques.
Advanced understanding of cloud and identity attack paths, including Microsoft Entra ID, Active Directory, privilege escalation, federation, service principals, conditional access weaknesses, and attack path analysis platforms.
Hands-on scripting or software engineering experience in languages such as Python, PowerShell, C#, Go, or JavaScript to support exploit development, automation, data analysis, and AI-enabled security workflows.
Working knowledge of AI security concepts, including OWASP Top 10 for LLM Applications, MITRE ATLAS, model evaluation methods, prompt engineering, adversarial testing, and responsible AI controls.
Bachelor’s degree in Computer Science or related field, or equivalent experience.
Advanced security certifications such as CISSP, GIAC, OSCP/OSCE, GWAPT, CISM, CRISC, CRTO, or similar.
Familiarity with regulatory and compliance frameworks (e.g., NIST, FFIEC, GLBA, SOX, PCI).

Responsibilities

Contribute to global Red Team and AI Red Team strategy, execution model, and operating standards.
Lead advanced attack simulations across traditional, cloud, and AI‑enabled environments.
Ensure red team activities align with enterprise risk, regulatory expectations, and control‑validation objectives.
Define multi-year technical capability roadmaps for red team operations, including cloud exploitation, identity attack paths, adversary simulation validation, AI security testing, and scalable tooling automation.
Lead and oversee complex red team engagements across network, endpoint, application, cloud, and physical attack surfaces.
Direct execution of advanced attack techniques including lateral movement, persistence, and control evasion.
Lead development and use of custom exploits, tooling, and methodologies to emulate real adversaries.
Provide hands-on technical leadership during complex engagements, including attack planning, exploit validation, payload development, command-and-control operations, and post-exploitation decision making.
Lead adversarial testing of AI and LLM systems (e.g., prompt injection, tool misuse, data leakage, and guardrail bypass).
Assess emerging technologies and platforms for exploitable weaknesses before and during enterprise adoption.
Integrate AI red team findings into enterprise risk, validation, remediation, and re-test workflows.
Evaluate AI-assisted developer tools (e.g., copilots) and automation platforms for security impact.
Assess how AI systems interact with identity, permissions, APIs, and enterprise data sources.
Use frontier and local LLM to augment red team capabilities and tools.
Design and execute AI-specific test cases for prompt injection, indirect prompt injection, model manipulation, jailbreak resistance, retrieval-augmented generation exposure, agentic workflow abuse, model supply chain risk, and sensitive data exfiltration.
Assess AI platforms across the full lifecycle, including model selection, training and fine-tuning data, system prompts, tool permissions, plugin integrations, API exposure, logging, monitoring, and human-in-the-loop controls.
Evaluate AI-assisted offensive and defensive tooling for operational value, misuse potential, data handling risk, and alignment with enterprise security governance.
Drive research into real‑world threat actor TTPs and emerging AI‑enabled attack techniques.
Sponsor development of red team tools, scripts, and repeatable methodologies to increase realism, scale, and efficiency.
Establish standards for tooling governance, safe use, and audit readiness.
Build and maintain secure development practices for internal red team tools, including code review, dependency management, secrets handling, operational security controls, and responsible use of AI-generated code.
Assist in developing senior and junior red team operators globally.
Contribute to executive‑level reporting of attack outcomes, business impact, and remediation validation.
Partner with stakeholders to ensure findings lead to sustained control improvements.