AI Security Red Team Engineer II

Fairygodboss; Plano (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

JPMorganChase is seeking a Security Engineer to join the Cybersecurity & Technology Controls for AI/ML. You will design secure AI/ML architectures, lead red teaming efforts, and work across product, data science, cyber, legal, and risk teams to policy and mitigate AI risks.

You will partner with platform and cloud security to ensure secure infrastructure, while advancing adversarial resilience and safe rollout of new AI models.

Qualifications

• Formal training or certification in Public Cloud concepts and hands-on experience with cloud-native AI services (e.g., Bedrock).
• Experience with threat modeling, discovery, vulnerability, and penetration testing (MITRE ATLAS, OWASP Top 10 for LLMs) and core security concepts (IAM, Authentication, OIDC, SAML).
• Practical IaC experience with Terraform and CloudFormation.
• Proficiency in Python scripting.
• Strong understanding of AI/ML concepts and AI red teaming foundations.

Responsibilities

• Develop and enhance security strategies, red teaming programs, and scalable solution designs.
• Design secure AI and software architectures; review designs and code for adversarial resilience.
• Reduce AI/LLM vulnerabilities by following standards, testing protocols, and policy controls.
• Collaborate with product, data science, cyber, legal, and risk teams to assess AI use cases and mitigations.
• Conduct discovery, threat modeling, and adversarial testing on generative AI, RAG pipelines, and ML systems.

Skills

Public Cloud concepts

Threat modeling

AI/ML concepts

Python scripting

Security architecture

Enterprise security problem solving

Tools

Terraform

CloudFormation

Bedrock

PyRIT

Garak

MITRE ATLAS

OWASP Top 10 for LLMs

Job description

JPMorganChase is seeking a Security Engineer to join the Cybersecurity & Technology Controls for AI/ML. You will design secure AI/ML architectures, lead red teaming efforts, and work across product, data science, cyber, legal, and risk teams to policy and mitigate AI risks.

You will partner with platform and cloud security to ensure secure infrastructure, while advancing adversarial resilience and safe rollout of new AI models.