Red Team Security Engineer
Core
Designing and executing adversarial testing, threat modeling, and security strategies for generative AI, LLMs, and ML systems to ensure adversarial resilience.
Role type
Senior IC Red Team Security Engineer (AI/ML)
Builds
Secure AI architectures, red teaming playbooks, automation tools, dashboards, and testing frameworks.
Domain
Financial Services / AI Security / Generative AI
Deliverable
production ML models | product features | research
Required skills
Threat modeling, penetration testing, vulnerability testing, Python scripting, Infrastructure as Code (Terraform, CloudFormation), IAM, OIDC, SAML, AI/ML concepts, prompt injection testing, jailbreaking detection, data poisoning detection
Preferred skills
Enterprise-scale AI red teaming exercise design, experience with PyRIT, Garak, custom LLM evaluation harnesses, open-source security contributions
Technologies
AWS Bedrock, PyRIT, Garak, MITRE ATLAS, OWASP Top 10 for LLMs, Terraform, CloudFormation, Python
Responsibilities
Design secure AI and software architectures and challenge designs/code for adversarial resilience; perform discovery, threat modeling, and adversarial testing on RAG pipelines and ML systems; define and implement AI red teaming methods and success measures; partner with stakeholders to understand AI use cases and recommend risk mitigation; build internal tools and automation for red teaming work; monitor emerging AI threats via external researchers and standards bodies.
Seniority
Senior, hands-on IC
