AI Architect

Role Overview

We are seeking an experienced AI Architect to lead the design and deployment of multi-agent AI systems, with a preference for healthcare use cases. This role focuses on deep agent architectures, supervisor/manager agents, and delivering solutions from concept to live production in enterprise environments.

Responsibilities

Architect agentic workflows using frameworks like LangGraph, AutoGen, Semantic Kernel, PydanticAI or CrewAI for stateful orchestration, supervisor routing, and reliable control flows.

Design and implement multi-agent teams (e.g., researcher, planner, coder, evaluator) with clear roles, goals, and collaboration patterns.

Integrate MCP (Model Context Protocol) for secure plugin and tool interoperability.

Apply advanced prompt engineering for rule extraction, content parsing, and dynamic task execution across agents.

Ensure production readiness: scalability, security, observability, cost optimization, and compliance with enterprise standards.

Collaborate with global stakeholders to deliver live deployments in cloud environments.

Drive continuous improvement by evaluating frameworks, optimizing agent reliability, and implementing guardrails for safe AI operations.

Required Skills

7+ years in software engineering; 2+ years architecting LLM-based or agentic systems.

Hands-on experience with frameworks such as LangChain/LangGraph, AutoGen, Semantic Kernel, and CrewAI.

Strong proficiency in Python; experience with cloud platforms (preferably Azure) and containerization (Docker/Kubernetes).

Expertise in multi-agent orchestration in production environments, prompt engineering for rule/content extraction, and RAGworkflows.