Advanced AI Security & LLM Architect

AnaVation, LLC; Reston (VA); On-site; USD 150,000 - 190,000; Full time

Benefits offered by this job

Generous medical insurance support

100% company-paid dental insurance

Disability insurance

Vision insurance

401k with match

Competitive pay

Paid leave and holidays

Tuition reimbursement

Life and AD&D

Job summary

AnaVation is seeking an AI Security & LLM Engineer to design, secure, and optimize our next-generation generative AI infrastructure. You will bridge advanced AI capabilities with rigorous cybersecurity practices, building resilient multi-agent systems and defending against prompt injection and data exfiltration.

You will work on architecture, defense, red teaming, performance optimization, and secure development to integrate frontier models into enterprise apps.

Qualifications

• Active TS/SCI Clearance with CI Polygraph.
• Bachelor's degree and 8 years of related experience.
• Certifications in IAT Level II and CSSP Infrastructure Support (CompTIA Cloud+).
• Multiple certifications across CS&A and cyber defense (e.g., CySA+, CND, GICSP).
• Hands-on AI architecture, AI security, and infrastructure management experience.

Responsibilities

• System Architecture: Design and deploy multi-agent orchestration frameworks and RAG pipelines.
• Adversarial Defense: Develop guardrails to neutralize prompt injection and adversarial attacks.
• Red Teaming: Conduct continuous LLM red teaming and simulations to find vulnerabilities.
• Performance Optimization: Manage token usage, reduce latency, and optimize API throttling.
• Secure Development: Write secure, production-grade code to integrate frontier models.

Skills

AI security

Red teaming

Multi-agent orchestration

Performance optimization

Education

Bachelor's degree

Tools

RAG pipelines

Security tooling

Job description

AnaVation is seeking an AI Security & LLM Engineer to design, secure, and optimize our next-generation generative AI infrastructure. You will bridge advanced AI capabilities with rigorous cybersecurity practices, building resilient multi-agent systems and defending against prompt injection and data exfiltration.

You will work on architecture, defense, red teaming, performance optimization, and secure development to integrate frontier models into enterprise apps.