AI-Focused Red Team Operator

Millennium Corporation • Washington, DC

5d • $130,000 - $133,000 • Onsite

About The Position

Millennium is hiring a skilled AI-Focused Red Team Operator to support advanced cyber operations for a government customer in the Washington, DC area. This role offers the opportunity to work at the forefront of AI-enabled cyber operations, combining traditional penetration testing, adversary emulation, threat hunting, and detection engineering with emerging AI technologies. The candidate will conduct authorized penetration testing, adversary emulation, and Red Team assessments against enterprise, cloud, and AI-enabled environments. They will also perform Blue Team activities including threat hunting, detection engineering, incident response support, and defensive security assessments. A key aspect of the role involves evaluating AI and machine learning systems for security weaknesses throughout the model lifecycle, assessing Large Language Model (LLM) applications against emerging AI threats and industry frameworks, and identifying vulnerabilities related to prompt injection, retrieval-augmented generation (RAG), model manipulation, indirect prompt injection, tool abuse, data poisoning, and model extraction techniques. The operator will develop offensive tradecraft for AI-enabled systems, design and implement defensive controls, and leverage AI technologies to enhance cyber operations. Collaboration with cybersecurity engineers, analysts, and stakeholders is crucial for improving organizational resilience, and the role requires producing high-quality technical documentation, assessment reports, and executive briefings. Additionally, successful candidates will demonstrate experience building or integrating AI-assisted security workflows, including agentic workflows, automated alert triage, detection tuning, AI-assisted report generation, secure LLM integration, and evaluation of security-focused language models.

Requirements

• Active Top Secret security clearance.
• Bachelor's and total 5+ years experience. Additional 4+ YoE would be considered in lieu of degree.
• Experience conducting Red Team operations, penetration testing, or adversary emulation.
• Design, develop, and evaluate AI agents capable of automating routine penetration testing tasks within authorized environments, employing strict operational guardrails, human oversight, and defined rules of engagement to ensure safe, controlled, and repeatable security assessments.
• Experience supporting Blue Team operations including threat hunting, detection engineering, incident response, or security operations.
• Strong understanding of enterprise networking, operating systems, identity management, cloud technologies, and modern attack methodologies.
• Experience developing scripts or automation using Python, PowerShell, Bash, or similar languages.
• Familiarity with AI/ML concepts, Large Language Models, and AI security risks.
• Strong written and verbal communication skills.

Nice To Haves

• Experience with AI Red Teaming
• Prompt injection testing
• Retrieval-Augmented Generation (RAG) security
• Adversarial machine learning
• Model evasion and data poisoning
• AI governance and secure model deployment
• MITRE ATT&CK
• MITRE ATLAS
• OWASP LLM Top 10
• NIST AI Risk Management Framework (AI RMF)
• One or more of the following certifications are desirable: CISSP or CEH or OSCP or GPEN or GCIH or PNPT or Security+ or AI Security coursework or certifications (e.g., AI Security Fundamentals, LLM Red Teaming, or equivalent training)

Responsibilities

• Conduct authorized penetration testing, adversary emulation, and Red Team assessments against enterprise, cloud, and AI-enabled environments.
• Perform Blue Team activities including threat hunting, detection engineering, incident response support, and defensive security assessments.
• Evaluate AI and machine learning systems for security weaknesses throughout the model lifecycle.
• Assess Large Language Model (LLM) applications against emerging AI threats and industry frameworks such as the OWASP LLM Top 10.
• Identify vulnerabilities involving prompt injection, retrieval-augmented generation (RAG), model manipulation, indirect prompt injection, tool abuse, data poisoning, and model extraction techniques.
• Develop offensive tradecraft to evaluate AI-enabled systems while ensuring responsible and authorized testing practices.
• Design and implement defensive controls including guardrails, monitoring, content filtering, evaluation frameworks, and AI-specific security controls.
• Leverage AI technologies to improve offensive and defensive cyber operations through automation, large-scale reconnaissance, code analysis, detection engineering, report generation, and security analytics.
• Collaborate with cybersecurity engineers, analysts, and stakeholders to improve organizational resilience against emerging AI-enabled threats.
• Produce high-quality technical documentation, assessment reports, and executive briefings.
• Assist with Business Development activities as required to support Millennium's strategic business objectives, which may include but not limited to participation in technical interviews, creation of technical documentation, general proposal writing support and proposal color reviews.

Benefits

• Millennium is an equal opportunity employer and does not discriminate or allow discrimination on the basis of race, color, religion, gender, age, national origin, citizenship, disability, veteran status or any other classification protected by federal, state, or local law.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior