Global Red Team AI Engineer, Analyst

MUFG•Jersey City, NJ

21h•Hybrid

About The Position

The Red Team Analyst supports MUFG Red Team operations by executing adversary-emulation activities focused on AI-enabled technologies. This role is designed for early-career professionals with a computer science background and practical coding experience, enabling them to develop offensive security skills while contributing to risk reduction across the enterprise. Under the direction of senior operators, the analyst participates in threat-led assessments, AI security testing, and purple team exercises, helping identify how real-world adversaries could exploit application logic, automation pipelines, and AI-assisted capabilities.

Requirements

Bachelor’s degree in Computer Science, Software Engineering, Computer Engineering, or equivalent practical experience.
Demonstrated experience through internships, co-ops, academic projects, or personal work.
Strong analytical skills, attention to detail, and willingness to learn adversarial thinking.
Hands-on experience with agentic AI, LLMs, and custom ML model development.
Proficiency with open-source AI frameworks and tooling (e.g., PyTorch, TensorFlow, SageMaker).

Nice To Haves

Familiarity with: REST APIs, OAuth/OIDC, JWT.
CI/CD pipelines or DevOps tooling.
Hands-on experience using or experimenting with AI/LLM tools or prompt-driven workflows.
Familiarity with enterprise cloud AI platforms (e.g., Azure AI Foundry, AWS Bedrock, or GCP Vertex AI).

Responsibilities

Participate in Red Team missions designed to simulate real-world attacker behavior against MUFG applications and platforms.
Execute assigned activities during: adversary simulation and emulation (ASE) assumed-breach scenarios purple team and control-validation exercises.
Safely conduct testing activities aligned to approved scopes, deconfliction requirements, and operational guardrails.
Support adversarial testing of AI-enabled capabilities, including: prompt injection and misuse scenarios unintended data access or disclosure via AI tools bypass of AI guardrails and safety controls.
Assist in assessing AI-assisted developer tools, copilots, and automation platforms.
Help evaluate how AI interacts with identity, permissions, APIs, and data sources.
Research emerging attacker techniques targeting: modern application stacks CI/CD and developer tooling AI/LLM systems.
Contribute to Red Team playbooks, test cases, and repeatable workflows.
Support senior operators in engagement reporting and evidence collection.
Participate in post-engagement discussions with defensive and engineering teams.
Develop and operationalize custom ML/LLM models for cybersecurity use cases.
Advance preventative, detective, and responsive security controls through applied AI innovation.
Evaluate emerging AI capabilities for cybersecurity and mature predictive, proactive threat response.