AI Security Engineer

Precise Software Solutions Inc. is seeking an AI Security Engineer to secure AI-enabled applications for the U.S. Government. You will lead security and compliance work for AI systems: getting them through the Authority to Operate (ATO) process, adversarial testing and red teaming of large language models, supply chain risk management, and AI incident response. This role ramps up around ATO milestones, major releases, and new AI use cases.

• Must be a U.S. citizen or lawful permanent resident (green card holder/EAD).
• Must reside in the Washington, DC metropolitan area and be able to work on-site at Government offices in DC 3 x a week.
• Must be able to obtain and maintain a NACI Tier 1 background investigation.

Key Responsibilities

• Support the NIST RMF ATO process for each AI system, including boundary definition, FISMA categorization, and authorization documents (SSP, SAR, POA&M).
• Plan and perform AI-specific adversarial testing and red teaming (prompt injection, jailbreak, data poisoning, model inversion/extraction, unsafe output, and unauthorized disclosure), and track findings through remediation.
• Assemble AI security certification packages, including vulnerability scan and penetration test results and POA&M updates, so that no High or Critical findings remain unmitigated at release.
• Implement and verify security controls for AI systems: Zero Trust and least-privilege access, FIPS-validated encryption, secrets management, secure LLM API key handling, and FedRAMP boundary and TIC compliance.
• Develop and maintain the AI Incident Response Plan and Business Continuity Plan; support incident triage, containment, and reporting within required timeframes; and lead post-incident reviews.
• Design security monitoring for AI workloads, including detection of prompt-injection attempts, jailbreaks, credential misuse, and vector database anomalies, plus compliance tracking of control drift.
• Support privacy documentation (PTA/PIA), significant-change notifications, annual assessments, and continuous monitoring reviews.
• Advise AI engineers during design and code reviews to build security in, and brief Government security staff on risks and mitigations.