Secure AI Engineer

Booz Allen Hamilton•Washington, DC

1d•$77,600 - $176,000•Hybrid

About The Position

Are you looking for an opportunity to use your knowledge and technical skills to help organizations adopt artificial intelligence (AI) securely and responsibly. As a Secure AI Engineer, you'll combine your skills in AI engineering, cybersecurity, and offensive security to assess, harden, and improve AI-enabled systems. You'll have the chance to build your skills and solve real-world challenges in a fast-paced, agile environment. We are looking for someone like you to work closely with clients to design secure AI architectures, evaluate AI system resilience, identify vulnerabilities, and implement mitigations that enable safe deployment of generative AI and autonomous AI capabilities. As a Secure AI Engineer on our team, you'll advise clients on the secure design, deployment, and governance of AI systems and generative AI applications. You'll conduct AI red team assessments against large language models (LLMs), retrieval-augmented generation (RAG) systems, AI agents, and multi-agent workflows. You will identify and demonstrate AI-specific attack vectors, including prompt injection, jailbreaks, indirect prompt injection, data poisoning, model inversion, extraction, and other adversarial techniques. You will develop recommendations and technical mitigations to improve AI system security, resilience, and trustworthiness. You will build, test, and evaluate agentic AI systems using modern orchestration frameworks and assess their security posture, design security testing methodologies, automation, and tooling for AI applications throughout the development lifecycle, and adapt and extend open-source AI frameworks, security tools, and evaluation platforms to meet client-specific requirements. You'll stay current with emerging AI threats, vulnerabilities, research, and industry best practices in this fast-paced world of AI. Join us. The world can’t wait.

Requirements

5+ years of experience building, deploying, or evaluating AI/ML systems
3+ years of experience developing applications using LLMs and modern AI frameworks
Experience with red teaming AI systems, Adversarial AI, or AI Governance
Knowledge of AI security principles, secure AI development practices, AI attack techniques, and AI risk management
Bachelor's degree

Nice To Haves

Experience with AI red teaming frameworks such as Microsoft's PyRIT, Garak, Inspect AI, OWASP GenAI tools, or similar platforms, working with open-source software, and modifying or extending existing frameworks to meet new use cases
Experience performing security assessments, penetration testing, or offensive security activities
Experience with agent orchestration frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, OpenAI Agents SDK, or similar technologies
Experience implementing security controls for RAG systems, vector databases, AI gateways, and model-serving infrastructure
Experience with containerization, Kubernetes, CI/CD pipelines, and Infrastructure-as-Code
Experience contributing to or maintaining open-source projects
Knowledge of AI security guidance and frameworks, including the OWASP Top 10 for LLM applications, NIST AI Risk Management Framework (RMF), MITRE ATLAS, and emerging AI security standards
Knowledge of adversarial machine learning concepts
Bachelor's degree in CS, Cybersecurity, or Engineering
CISSP, OSCP, Security+, GIAC, or Cloud Security Certifications

Responsibilities

Advise clients on the secure design, deployment, and governance of AI systems and generative AI applications.
Conduct AI red team assessments against large language models (LLMs), retrieval-augmented generation (RAG) systems, AI agents, and multi-agent workflows.
Identify and demonstrate AI-specific attack vectors, including prompt injection, jailbreaks, indirect prompt injection, data poisoning, model inversion, extraction, and other adversarial techniques.
Develop recommendations and technical mitigations to improve AI system security, resilience, and trustworthiness.
Build, test, and evaluate agentic AI systems using modern orchestration frameworks.
Assess the security posture of AI systems.
Design security testing methodologies, automation, and tooling for AI applications throughout the development lifecycle.
Adapt and extend open-source AI frameworks, security tools, and evaluation platforms to meet client-specific requirements.
Stay current with emerging AI threats, vulnerabilities, research, and industry best practices.