Secure AI Engineer: Red Team & Safe AI Architect

Booz Allen Hamilton; Washington (District of Columbia); On-site; USD 78,000 - 176,000; Full time

Job summary

Booz Allen Hamilton is seeking a Secure AI Engineer to help clients adopt artificial intelligence securely and responsibly. You will combine AI engineering, cybersecurity, and offensive security to assess and harden AI-enabled systems, designing secure architectures and governance frameworks.

You will conduct AI red team assessments, identify attack vectors, and implement mitigations to enable safe deployment of generative AI and autonomous AI capabilities.

Qualifications

• 5+ years of experience building, deploying, or evaluating AI/ML systems.
• 3+ years of experience with LLMs and modern AI frameworks.
• Experience with red teaming AI systems, adversarial AI, or AI governance.
• Bachelor's degree in CS, Cybersecurity, or Engineering or related field.

Responsibilities

• Design secure AI architectures and governance for AI systems.
• Evaluate AI system resilience and identify vulnerabilities.
• Develop mitigations and secure deployment practices for AI applications.

Skills

AI/ML systems

LLMs

AI security

Red teaming

Governance

Education

Bachelor's degree

Certifications (CISSP/OSCP)

Tools

LangGraph

CrewAI

AutoGen

Semantic Kernel

OpenAI SDK

Job description

Booz Allen Hamilton is seeking a Secure AI Engineer to help clients adopt artificial intelligence securely and responsibly. You will combine AI engineering, cybersecurity, and offensive security to assess and harden AI-enabled systems, designing secure architectures and governance frameworks.

You will conduct AI red team assessments, identify attack vectors, and implement mitigations to enable safe deployment of generative AI and autonomous AI capabilities.