DirectJobHub
Jobs · Art & Creative · Colorado

Principal Agentic AI Architect - Aurora CO or Meridian, CO

ICR, Inc. · Aurora, CO · 4 mo ago
HybridArt & Creative$160k–$210k/yrFull-time

Position Overview

We are seeking a visionary Principal Agentic AI Architect to lead the design and implementation of next-generation AI efforts for the Intelligence Community. In this role, you will define the architectural blueprint for a secure, multi-agent ecosystem that transforms natural language intent into auditable, multi-step operational workflows. You will not just build models; you will engineer collaborative agent teams, governance loops, and dynamic tool integration frameworks using open standards (MCP, A2A).

Key Responsibilities

  • Architectural Leadership: Define the end-to-end architecture, leveraging enterprise agent frameworks to enable dynamic, scalable multi-agent teams.

  • Agentic Orchestration: Design complex reasoning loops where specialized agents collaborate, manage shared memory/context, and execute tasks autonomously while maintaining human-in-the-loop control.

  • Governance & Safety: Engineer and enforce rigorous quality assurance (groundedness, safety, compliance) prior to result delivery, including automated rework loops.

  • Integration Strategy: Architect the Agent Gateway and Tool Registries to facilitate secure, dynamic discovery and execution of external tools via Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards.

  • Infrastructure Alignment: Lead integration efforts with an enterprise infrastructure platform infrastructure, including secure LLM hosting environment (LLM hosting), identity management system (Identity), and serverless compute environments.

  • Context Management: Develop robust strategies for short-term and long-term memory management to prevent context overflow in complex, multi-turn missions.

  • Observability & Ops: Implement comprehensive tracing and metrics to provide full visibility into agent decision paths, tool usage, and lifecycle health.

  • Mentorship: Guide a team of AI engineers and data scientists, fostering a culture of innovation, security-first thinking, and technical excellence.

  • Communication: Primary interface with Government customers on technology, roadmaps, and implementation details. Strong communications and briefing skills and able to communicate complex Agentic AI topics to a non-technical customer.

  • Agility: Flexibility and ability to adapt to evolving requirements and shifting priorities while effectively balancing multiple responsibilities.

Required Skillsets & Qualifications

  • Education Required: Master's degree or Ph.D. in Computer Science, Artificial Intelligence, Distributed Systems, or a related technical field.

  • Substitution: Equivalent practical experience (12+ years) in AI architecture and system design may substitute for advanced degrees.

  • Core Technical Competencies (Must-Have):

    • Agentic Frameworks: Deep, hands-on expertise with enterprise agent frameworks. Must demonstrate understanding of agent state management, handoffs, and collaborative reasoning.

    • LLM Operations: Proven experience deploying and optimizing LLMs in production, including prompt engineering, RAG (Retrieval-Augmented Generation), and model switching strategies.

    • Integration Protocols: Expert-level knowledge of MCP and emerging A2A standards. Experience building custom connectors and gateways is essential.

    • Distributed Systems: Strong background in microservices architecture, event-driven design, and containerization (Kubernetes/Docker).

    • Memory & Context: Demonstrated ability to architect vector databases, graph databases, and hybrid memory systems for maintaining long-term agent context.

    • Security & Compliance: Extensive experience implementing Zero Trust architectures and standards-based authentication & access controls in high-security environments. Experience working within the U.S. Intelligence Community (IC) or Department of Defense (DoD) on classified programs (TS/SCI).

PREFERRED SKILLS

  • Experience with enterprise infrastructure platform ecosystem tools (secure LLM hosting environments, identity management systems).

  • Contributions to open-source AI projects or standards bodies (e.g., contributing to MCP specs).

  • Experience with Agents-as-Code (AaaC) paradigms.

  • Proficiency in Python, Go, or Rust for high-performance agent runtime development.

Benefits

  • Comprehensive benefits package that includes company equity, retirement plan, company-paid health care benefits, a flexible paid time off policy, and opportunity for a raise and bonus during the year.

Similar jobs