Global Red Team Senior AI Engineer, Vice President
Mitsubishi UFJ Financial Group2 hours ago
Jersey City, NJ, USAStaff+
Responsibilities
- Lead global red team and AI red team strategy, operating standards, and multi-year technical capability roadmaps.
- Direct advanced attack simulations across network, endpoint, application, cloud, physical, identity, and AI-enabled environments.
- Provide hands-on leadership for attack planning, exploit validation, payload development, command-and-control operations, and post-exploitation decisions.
- Conduct adversarial testing of AI and LLM systems, including prompt injection, jailbreaks, agent abuse, data leakage, model manipulation, and supply-chain risks.
- Evaluate AI platforms, developer copilots, automation tools, model access controls, tool permissions, plugins, APIs, logging, monitoring, and human-in-the-loop controls.
- Research threat-actor tactics and AI-enabled attack techniques and sponsor development of secure red team tools, scripts, and methodologies.
- Mentor red team operators and translate attack outcomes into executive-level risk narratives, control validation results, and remediation priorities.
Requirements
- 7+ years of red team and offensive security experience, including leadership of advanced attack simulations.
- Demonstrated ability to execute attacks that evade network, endpoint, application, and cloud controls.
- Hands-on experience with AI red teaming, adversarial testing, LLM security assessments, AI-enabled applications, LLM agents, retrieval-augmented generation systems, and enterprise data connectors.
- Deep knowledge of application security vulnerabilities, exploitation techniques, web/API workflows, offensive tooling, implants or loaders, and modern command-and-control frameworks.
- Strong operational knowledge of Windows and Linux, including persistence, lateral movement, cloud and identity attack paths, Microsoft Entra ID, Active Directory, privilege escalation, federation, service principals, and conditional access weaknesses.
- Scripting or software engineering experience with languages such as Python, PowerShell, C#, Go, or JavaScript.
- Working knowledge of OWASP Top 10 for LLM Applications, MITRE ATLAS, model evaluation, prompt engineering, adversarial testing, and responsible AI controls.
- Ability to communicate technical attack results as executive-level risk narratives and prioritized remediation actions.
- Bachelor’s degree in Computer Science or a related field, or equivalent experience; advanced security certifications and familiarity with NIST, FFIEC, GLBA, SOX, or PCI are preferred.
Benefits
- Hybrid schedule requiring four days on-site and one day remote per week.
- Comprehensive health and wellness benefits, retirement plans, educational assistance, and training programs.
- Income replacement for qualified employees with disabilities, paid maternity and parental bonding leave, and paid vacation, sick days, and holidays.
- The role may be eligible for discretionary performance-based bonus or incentive compensation.