GenAI Architect - Agentic AI (Azure & Google AI)

We are looking for a hands-on GenAI Architect to lead the design and implementation of agentic AI systems across Azure OpenAI and Google Cloud AI (Vertex AI, Gemini). You will develop advanced orchestrated reasoning workflows powered by autonomous agents, orchestrator frameworks, and Model Context Protocols (MCP) that enable seamless collaboration between agents and models.

This role involves architecting and delivering Mixture of Experts (MoE) based solutions to dynamically select models or agents, and driving automation for enterprise domains such as IT, HR, and Business Analytics. You will work across the full stack of GenAI infrastructure designing agents that think, reason, and act across cloud platforms.

Key Responsibilities:

• Architect and build agentic AI workflows using orchestrator agents, reasoning engines, and tool-using sub-agents.
• Design and implement Model Context Protocol (MCP) layers to manage shared context and intent handoffs across multi-agent systems.
• Leverage Mixture of Experts (MoE) frameworks to intelligently route prompts and tasks to the most capable model or agent.
• Develop orchestrator agents that can coordinate tasks among multiple domain-specific agents and tools.
• Build workflows that solve complex enterprise problems in IT ticket triage, HR onboarding, policy QA, and analytics automation.
• Use frameworks like LangChain, CrewAI, AutoGen, or Semantic Kernel to build agent pipelines and reasoning flows.
• Integrate agents with enterprise platforms (e.g., ServiceNow, Workday, SAP, Microsoft Graph, Google Cloud Platform/Azure DevOps).
• Design robust reasoning systems that blend symbolic logic, memory, tool use, and chain-of-thought prompting.
• Deploy and manage LLM-based solutions on Azure OpenAI and Google Vertex AI/Gemini, ensuring scalability, governance, and performance.
• Create technical documentation, reusable components, and architectural blueprints for enterprise-wide use.

Required Qualifications:

• 7 years of experience in software development or AI architecture roles.
• At least 2 years building LLM-based or agentic AI solutions in production.
• Strong experience with Azure OpenAI, Google Vertex AI, and cloud-native application design.
• Deep understanding of Model Context Protocols (MCP) and how they facilitate coordination and memory in agentic systems.
• Proven experience implementing Mixture of Experts architectures or intelligent task-routing across agents/models.
• Fluency in Python and experience with LLM orchestration frameworks (e.g., LangChain, AutoGen, Semantic Kernel).
• Familiarity with vector databases (FAISS, Pinecone, Weaviate) and prompt engineering best practices.
• Experience integrating AI solutions with enterprise systems and APIs.