Principal Agentic AI Architect - Aurora CO or Meridian, CO
$160,000–$210,000 year
On-site · Aurora, Colorado, United States or Meridian, Colorado, United States
Job Summary
Lead architectural design and hands-on development of a secure, multi-agent AI ecosystem for the Intelligence Community. Define end-to-end architecture leveraging enterprise agent frameworks to enable dynamic, scalable multi-agent teams, agentic orchestration of complex reasoning with human-in-the-loop control, governance and safety QA, secure integration via MCP/A2A, and enterprise infrastructure alignment (secure LLM hosting, identity management, serverless compute). Drive context management strategies for short/long-term memory, observability of agent decision paths and tool usage, and mentorship of AI engineers/data scientists. Communicate technology roadmaps and implementation details to government customers; must thrive in high-security, classified environments and maintain Zero Trust compliance. Requirements include active TS/SCI with polygraph, US citizenship, advanced degree or equivalent experience, 10+ years software eng, 5+ years AI/ML architecture, 3+ years autonomous agent deployments, and experience in IC/DoD contexts.
Required Qualifications
- Active TS/SCI with Polygraph (Must be current and transferable)
- Requires US Citizenship
- Master's degree or Ph.D. in Computer Science, Artificial Intelligence, Distributed Systems, or related technical field (or equivalent practical experience: 12+ years)
- Minimum 10+ years of total software engineering experience
- Minimum 5+ years specifically focused on AI/ML system architecture
- Minimum 3+ years designing and deploying autonomous or semi-autonomous agent systems in production environments
- Demonstrated experience working within the U.S. Intelligence Community (IC) or Department of Defense (DoD) on classified programs (TS/SCI)
- Proficiency with Enterprise agent frameworks, LLM operations (prompt engineering, RAG, model switching), MCP and A2A standards
- Experience with distributed systems (microservices, event-driven design, Kubernetes/Docker)
- Memory/context management (vector/graph databases, long-term memory)
- Security & Compliance: Zero Trust architectures and standards-based authentication & access controls
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.