AI Solution Architect - Agentic AI

Role Overview

Key Responsibilities

• Design multi-agent roles, coordination patterns, and handoff logic using frameworks such as LangGraph, AutoGen, and CrewAI.
• Own task decomposition, tool calling, memory and state management, including knowledge graphs for structured reasoning.
• Define guardrails, tool-use permissions, kill switches, and escalation paths for agent failures.
• Architect evaluation frameworks for agentic systems with AI Assurance and QA.
• Lead technical design reviews before agent-based solutions reach build.
• Design fallback and human-in-the-loop patterns for high-stakes decisions.
• Mentor GenAI Engineers and review their architecture designs.
• Present risk and benefit tradeoffs to client technical and business stakeholders.
• Own architecture governance and facilitate reviews with Security, Governance, and Platform Engineering.

Requirements and Skills

• Require 10–15 or more years of software or AI architecture experience, including at least 2 years in agentic or multi-agent systems.
• Require deep knowledge of orchestration frameworks and failure modes such as loops, deadlocks, and drift.
• Architect across managed platforms including Azure AI Foundry Agent Service, AWS Bedrock Agents or Strands Agents, and Google Vertex AI Agent Builder.
• Strong systems-design fundamentals in distributed systems, state machines, and event-driven architecture.
• Experience with vector and graph-based memory architectures, agent evaluation, benchmarking, and governance tooling.
• Must communicate architecture decisions clearly, mentor or lead technical teams, and own production outcomes.