Hybrid Secure AI Engineer — Build Safe, Trustworthy AI

Booz Allen Hamilton; Washington; Hybrid; USD 78,000 - 176,000; Full time

Benefits offered by this job

Health benefits

Paid leave

Tuition assistance

Professional development

Job summary

Booz Allen Hamilton seeks a Secure AI Engineer to help clients design secure AI architectures, evaluate resilience, and implement mitigations for safe deployment of generative AI and autonomous AI capabilities.

You will conduct AI red team assessments against LLMs, RAG systems, and multi-agent workflows, identify attack vectors, and develop technical mitigations. Hybrid work in the Washington, DC area is typical.

Qualifications

• 1+ years of experience with LLMs and modern AI frameworks.
• 1+ years of experience building/evaluating agentic AI systems.
• Knowledge of AI security principles, AI risk management.

Responsibilities

• Advise clients on secure design, deployment, and governance of AI systems.
• Conduct AI red team assessments against LLMs, RAG systems, AI agents, and multi-agent workflows.
• Develop mitigations to improve AI security, resilience, and trust.
• Extend open-source AI frameworks and evaluation platforms to client needs.

Skills

LLM development

Agentic AI systems

AI security

Education

Bachelor's degree in CS/Engineering

Tools

LangGraph

CrewAI

Semantic Kernel

OpenAI Agents SDK

Job description

Booz Allen Hamilton seeks a Secure AI Engineer to help clients design secure AI architectures, evaluate resilience, and implement mitigations for safe deployment of generative AI and autonomous AI capabilities.

You will conduct AI red team assessments against LLMs, RAG systems, and multi-agent workflows, identify attack vectors, and develop technical mitigations. Hybrid work in the Washington, DC area is typical.