AI Solution Architect - Agentic AI

We are seeking a seasoned Software/AI Architect with extensive experience in designing and leading multi-agent and agentic workflow systems. This role focuses on developing the orchestration layers, memory architectures, and tool-use permissioning that ensure autonomous systems remain reliable, safe, and efficient. The ideal candidate will have a strong background in agent orchestration frameworks, distributed systems, and governance tooling, with a proven ability to guide technical teams and engage with stakeholders at all levels.

Key Responsibilities

- Design multi-agent architectures, including defining agent roles, coordination patterns, and handoff logic using platforms such as LangGraph, AutoGen, and CrewAI.
- Own the design of agentic workflows encompassing task decomposition, tool invocation, memory and state management, and the use of knowledge graphs for structured reasoning and long-term memory retention.
- Define and implement guardrails such as tool-use permissioning, kill switches, and escalation paths to manage agent failures effectively.
- Architect evaluation frameworks for agentic systems in collaboration with AI Assurance and Quality Assurance teams.
- Lead technical design reviews for agent-based solutions prior to development, ensuring robustness and alignment with best practices.
- Develop fallback mechanisms and human-in-the-loop patterns for critical agent decisions where high stakes are involved.
- Mentor GenAI Engineers on architectural patterns and provide detailed design reviews to elevate team capabilities.
- Present risk and benefit analyses of agentic systems to both technical and business stakeholders, facilitating informed decision-making.
- Own architecture governance for agentic builds across the practice, ensuring consistency and compliance.
- Facilitate cross-team design reviews involving Security, Governance, and Platform Engineering to maintain alignment and address concerns proactively.

Required Qualifications

- 10 to 15+ years of experience in software or AI architecture, with at least 2 years specifically focused on agentic or multi-agent systems.
- Deep expertise in agent orchestration frameworks and a thorough understanding of their failure modes, including loops, deadlocks, and drift.
- Experience evaluating and architecting solutions on managed agentic platforms such as Microsoft Azure AI Foundry Agent Service, AWS Bedrock Agents/Strands Agents, Google Vertex AI Agent Builder, as well as open-source orchestration tools like LangGraph, AutoGen, and CrewAI.
- Strong fundamentals in systems design, including distributed systems, state machines, and event-driven architectures.
- Proven experience designing memory architectures for long-running agents, utilizing vector and graph-based approaches.
- Familiarity with agent evaluation methodologies and benchmarking techniques to assess system performance and reliability.
- Working knowledge of guardrail and governance tooling specific to agentic systems.
- Ability to confidently defend architectural decisions under adversarial technical scrutiny from client architects.
- Skilled in writing clear Architecture Decision Records (ADRs) and documentation accessible to both engineers and executives.
- Demonstrated experience mentoring and leading technical teams, not limited to solo design work.
- Comfortable taking accountability as the technical owner when agentic systems encounter production failures.

This role offers the opportunity to lead cutting-edge architectural initiatives in autonomous systems, working at the intersection of AI innovation and operational excellence. If you thrive in complex, high-impact environments and possess a deep technical acumen combined with leadership skills, this position is an excellent fit.