Agentic AI Security Engineer, Lead
Booz Allen Hamilton2 days ago
Base Salary
$99k - $225k/yr
Responsibilities
- Design and validate secure architectures for generative AI applications, AI agents, and multi-agent systems.
- Develop prototypes and reference implementations for AI security controls and architectural tradeoffs.
- Assess AI systems for prompt injection, sensitive data exposure, excessive permissions, unsafe tool execution, and compromised integrations.
- Implement controls for agent identity, least privilege, execution isolation, tool authorization, data protection, and human approval.
- Create architecture diagrams, data flow diagrams, trust boundary models, and technical documentation.
- Establish evaluation and monitoring approaches for agent behavior, security, reliability, policy compliance, and traceability.
- Translate security and governance requirements into engineering practices, including testing, version control, change management, audit trails, and rollback procedures.
- Evaluate emerging models, agent frameworks, integration protocols, and security tools and communicate recommendations.
- Provide technical leadership, conduct design reviews, guide architectural decisions, and raise the team's technical standards.
Requirements
- 8+ years of software engineering or AI/ML engineering experience, including developing and deploying AI/ML systems.
- Experience developing in Python and using Git, automated testing, code review, and dependency management.
- Experience building large-language-model applications involving tool use, retrieval-augmented generation, and agent orchestration.
- Experience designing or evaluating architectures involving APIs, data pipelines, model services, and enterprise integrations.
- Experience applying cybersecurity principles including identity and access management, trust boundaries, secure data handling, and threat modeling.
- Experience with traditional machine learning approaches and their cybersecurity applications.
- Knowledge of NIST SP 800-53, the AI Risk Management Framework, and Zero Trust Architecture principles.
- Knowledge of security risks and mitigation approaches for generative AI and agentic systems.
- Ability to obtain a Secret clearance; TS/SCI clearance is a preferred qualification.
- Bachelor's degree in computer science, mathematics, engineering, or cybersecurity.
- Preferred experience with Strands Agents, LangGraph, Amazon Bedrock, GraphRAG, Temporal, Model Context Protocol, AI red teaming, adversarial testing, AI gateways, policy enforcement, execution sandboxes, agent observability, human-in-the-loop controls, cloud or on-premises deployment, containers, model training or serving, distributed computing, data engineering, feature pipelines, and relational or vector databases.
Benefits
- Health, life, disability, financial, and retirement benefits are offered.
- Paid leave, professional development, tuition assistance, work-life programs, and dependent care are available.
- Recognition awards may be provided for exceptional performance and demonstration of company values.
- Regular full-time and part-time employees working at least 20 hours per week are eligible for the applicable benefits program.
- Work-model expectations vary by designation: remote roles may occasionally require in-person work, hybrid roles require facility work according to leadership and role needs, and onsite roles are primarily performed at a customer facility.
Categories
About Booz Allen Hamilton
Booz Allen Hamilton builds and integrates software, analytics, AI, cloud, and cybersecurity solutions while providing engineering and consulting services, primarily for U.S. defense, intelligence, and civil government clients, with select commercial partnerships. Its business is largely government contracting and professional services delivering mission systems and cyber defense. Founded in 1914 and headquartered in McLean, Virginia, Booz Allen is a public company traded on the NYSE (ticker: BAH).