AI Solution Architect – Agentic AI

About the role

We are seeking an AI Solution Architect specialized in agentic AI to design and govern multi‑agent workflow systems that are reliable, safe, and scalable. The role combines deep technical expertise with leadership across engineering, security, and governance teams.

Key responsibilities

• Design multi‑agent architectures (agent roles, coordination patterns, handoff logic) using frameworks such as LangGraph, AutoGen, and CrewAI.
• Own agentic workflow design: task decomposition, tool‑calling, memory/state management, including knowledge graphs for structured reasoning and long‑term memory.
• Define guardrails: tool‑use permissioning, kill switches, and escalation paths for agent failure.
• Architect evaluation frameworks for agentic systems in partnership with AI Assurance/QA.
• Lead technical design reviews for agent‑based solutions before they enter build.
• Design fallback and human‑in‑the‑loop patterns for high‑stakes agent decisions.
• Mentor GenAI Engineers on architecture patterns and review their designs.
• Present risk/benefit trade‑offs of agentic systems to client technical and business stakeholders.
• Own architecture governance for agentic builds across the practice.
• Facilitate cross‑team design reviews involving Security, Governance, and Platform Engineering.

Required profile

• 10–15+ years of software/AI architecture experience, with at least 2 years focused on agentic or multi‑agent systems.
• Proven ability to lead technical design reviews and mentor engineering teams.
• Strong communication skills to present complex trade‑offs to both technical and business audiences.
• Experience taking accountability for production‑grade agentic systems.
• Ability to defend architecture decisions under adversarial technical challenge.

Required skills

• LangGraph, AutoGen, CrewAI orchestration frameworks.
• Microsoft Azure AI Foundry Agent Service.
• AWS Bedrock Agents / Strands Agents.
• Google Vertex AI Agent Builder.
• Distributed systems, state machines, event‑driven architecture.
• Vector‑based and graph‑based memory architectures.
• Knowledge‑graph construction for reasoning.
• Agent evaluation methodologies and benchmarking.
• Guardrail and governance tooling for agentic systems.
• Writing Architecture Decision Records (ADRs) and clear documentation.