Frontier AI Offensive Engineer - Secure AI Testing

State Street; Clifton (NJ); On-site; USD 120,000 - 203,000; Full time

Job summary

State Street's Frontier AI Security & Testing (FAST) team is hiring an Offensive AI Engineer to design, deploy and secure AWS-based frontier AI platforms and evaluation harnesses. You will build model onboarding flows, evaluation frameworks and agentic workflows to support adversary simulation in a regulated financial services environment.

The role emphasizes hands-on engineering, debugging, automation, and governance to ensure auditable and compliant AI usage across enterprise systems and

Qualifications

• 5+ years hands-on experience in software, cloud, data or security engineering.
• 2+ years building GenAI/LLMs or agentic AI on cloud platforms (prefer AWS).
• Experience with infrastructure-as-code and CI/CD tooling.
• AWS certifications and/or Databricks certifications are a plus.
• Offensive security certifications or pentesting experience is a plus.
• Financial services or regulated industry experience preferred.

Responsibilities

• Design, deploy and operate secure AWS environments for frontier AI models and evaluation harnesses.
• Develop frontier model engineering and evaluation pipelines.
• Build Databricks pipelines to ingest and analyze model telemetry and security data.
• Create secure API integrations between AI platforms and enterprise systems.
• Implement logging, governance and controls for auditable AI use.

Skills

AWS

Databricks

Python

REST API

AI security

Education

Bachelor's in CS/Engineering

Tools

Terraform

CI/CD

Bedrock

SageMaker

KMS

VPC

Job description

State Street's Frontier AI Security & Testing (FAST) team is hiring an Offensive AI Engineer to design, deploy and secure AWS-based frontier AI platforms and evaluation harnesses. You will build model onboarding flows, evaluation frameworks and agentic workflows to support adversary simulation in a regulated financial services environment.

The role emphasizes hands-on engineering, debugging, automation, and governance to ensure auditable and compliant AI usage across enterprise systems and