Offensive AI Engineer – Frontier AI Security & Testing, VP

State Street

. Design, engineer and deploy secure, isolated AWS environments for frontier AI models .

Posted 10/9/2026full-timeUnited StatesLead💰 $120,000 - $202,500 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and deploying secure AWS environments for AI models, with a strong focus on infrastructure-as-code, CI/CD pipelines, and AI security practices. Proficient in statistical analysis, model evaluation, and building integrations across AI platforms and enterprise systems.

Highest-signal resume keywords

AWS Environment DesignInfrastructure-as-CodeGenAI and LLM SolutionsPython ProgrammingOffensive Security Concepts

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

AWSPythonDatabricksTerraformREST APIsStatistical AnalysisCI/CD PipelinesAgentic WorkflowsModel EvaluationNetwork Segmentation

Soft Skills

Critical ThinkingProblem-SolvingTechnical Communication

Tools & Technologies

Amazon BedrockSageMakerLambdaAPI GatewayEKS/ECSIAMKMSVPC NetworkingPySparkDelta Lake

Certifications & Qualifications

AWS CertificationDatabricks CertificationOffensive Security Certification

Industry Keywords

AI Security RisksCompliance RequirementsFinancial ServicesMITRE ATT&CKOWASP Top 10

Tech Stack

Tools & technologies

AWSCloudPySparkPythonSQLTerraform

About the role

Key responsibilities & impact

Design, engineer and deploy secure, isolated AWS environments for frontier AI models
Build and maintain infrastructure-as-code and CI/CD pipelines for AI workloads
Engineer network segmentation, identity and access controls, secrets management and egress restrictions
Integrate frontier model provider APIs and SDKs and build model-agnostic abstraction layers
Design and build evaluation harnesses and benchmarking frameworks for offensive security tasks
Develop agentic workflows, tool-use integrations and multi-agent orchestration for reconnaissance, attack-path analysis and adversary simulation
Stress-test models for prompt injection, jailbreak susceptibility, data leakage, tool misuse, scope drift and unsafe emergent behavior
Design and build Databricks pipelines to ingest, curate and analyze model telemetry and evaluation data
Apply statistical comparison, scoring, trend analysis and regression detection across model versions
Build data products and dashboards showing model performance, cost and risk
Build secure integrations between AI platforms, enterprise systems, security tools and data sources
Develop reusable API patterns and connectors for tool invocation, context injection and output validation
Implement AI guardrails, human-in-the-loop checkpoints, rate and scope limits, kill switches and least-privilege tool access
Engineer logging, monitoring and observability for agent inputs, outputs, tool calls and decision paths
Align AI use with Responsible AI, model risk management, legal and compliance requirements
Produce technical evidence for audit and regulatory review
Document architectures, controls and evaluation methods

Requirements

What you’ll need

Bachelor's degree in Computer Science, Engineering, Data Science, Information Systems, Artificial Intelligence, or equivalent practical experience
5+ years of hands-on experience in software, cloud, data or security engineering
2+ years of hands-on experience building and deploying GenAI, LLM or agentic AI solutions on cloud platforms, preferably AWS
Deep hands-on experience deploying AI-enabled applications on AWS, particularly Amazon Bedrock, SageMaker, Lambda, API Gateway, EKS/ECS, IAM, KMS and VPC networking
Direct experience working with frontier LLMs through vendor APIs, including prompt and context engineering, tool use and function calling, agentic workflows and model evaluation
Strong Python skills
Experience with GenAI and agentic frameworks such as LangChain, LangGraph, Strands, CrewAI, Pydantic and MCP, or similar
Hands-on Databricks experience with PySpark, SQL, Delta Lake and workflows
Working grounding in data science and statistical analysis
Experience designing and consuming REST APIs and event-driven integrations
Working understanding of AI security risks and controls, including OWASP Top 10 for LLM Applications, MITRE ATLAS and NIST AI RMF
Familiarity with offensive security concepts, adversary tactics and MITRE ATT&CK is strongly preferred
Experience with infrastructure-as-code, preferably Terraform, and CI/CD tooling
AWS and/or Databricks certifications are a plus
Offensive security certifications or penetration testing experience are a plus
Experience in financial services or another highly regulated industry is preferred
Strong critical thinking, problem-solving and technical communication skills
Ability to research, learn and apply new models, tools and techniques quickly

Benefits

Comp & perks

Retirement savings plan (401K) with company match
Basic life insurance
Medical insurance
Dental insurance
Vision insurance
Long-term disability insurance
Optional additional insurance coverages
Paid vacation leave
Paid sick leave
Short-term disability
Family care leave/support
Employee Assistance Program
Incentive compensation, including eligibility for annual performance-based awards
Tax-advantaged savings plans
Inclusive development opportunities
Flexible work-life support
Paid volunteer days
Employee networks