AI Security & LLM Engineer

Description of Task to be Performed:

The AI Security & LLM Engineer will design, secure, and optimize our next-generation generative AI infrastructure. In this role, you will bridge the gap between advanced AI capabilities and rigorous cybersecurity practices. You will build resilient multi-agent systems while actively defending against emerging vulnerabilities like prompt injection, data exfiltration, and model manipulation.

Core Responsibilities:

• System Architecture: Design and deploy robust multi-agent orchestration frameworks and Retrieval-Augmented Generation (RAG) pipelines.
• Adversarial Defense: Develop, implement, and maintain advanced input/output guardrails to neutralize prompt injection and adversarial attacks.
• Red Teaming: Conduct continuous LLM red teaming and simulations to identify system vulnerabilities and structural weaknesses.
• Performance Optimization: Manage token usage, reduce latency, and engineer efficient API rate limit management strategies.
• Secure Development: Write clean, secure, and production-grade code to integrate frontier models into enterprise applications.

Primary Languages & Technical Stack

• Rust or Python (at least one required)

Required Qualifications:

• Clearance: Active TS/SCI Clearance with CI Polygraph
• Education & Years of Experience: Bachelor’s degree and 8 years of experience related to specific functional area.
• Certifications: Active certifications for both IAT Level II (e.g. CompTIA Security+) and Cyber Security Service Provider (CSSP) Infrastructure Support (e.g. CompTIA Cloud+) by program onboarding date.
• The following individual certifications cover both certification requirements for this program: CompTIA Cybersecurity Analyst, CySA+; EC-Council Certified Network Defender (CND); GlAC Global Industrial Cyber Security Professional, GICSP; (ISC)2 System Security Certified Practitioner (SCCP).
• Hands-on experience and knowledge with the following:
• AI Architecture: Proven experience with multi-agent orchestration tools and production-grade RAG pipelines.
• AI Security: Deep understanding of OWASP Top 10 for LLMs, prompt injection defense, and guardrail frameworks.
• Infrastructure Management: Experience handling token optimization, context window constraints, and API throttling.

Preferred Qualifications:

• Frontier Model Expertise: Hands-on experience deploying commercial frontier models (e.g., ChatGPT, Grok, Claude).
• AI Developer Tools: Experience utilizing advanced AI-assisted development workflows such as Claude Code or Codex.
• Security Testing: Background in traditional penetration testing, vulnerability assessment, or cryptographic concepts.