Gen AI Enterprise Architect

Role

Lead the design and deployment of production-grade Generative AI and complex conversational systems, focusing on agentic orchestration, state and session management, cloud deployment, and evaluation methodologies for LLM-powered applications.

Key Responsibilities

• Design and deploy production-grade generative AI and conversational systems.
• Architect agentic orchestration workflows using frameworks and patterns (e.g., LangGraph, AutoGen, CrewAI; ReAct, CoT).
• Define and implement state management and session management for agentic workflows.
• Build REST APIs and backend services using Python frameworks (Flask or FastAPI).
• Deploy and manage AI workloads on major cloud platforms with containerization (Docker, Kubernetes).
• Integrate with MCP systems and develop MCP tool layers.
• Define evaluation methodologies for RAG and other LLM-powered applications.
• Implement or advise on agent observability and monitoring solutions.

Requirements

Must have

• Experience designing and deploying production-grade Generative AI or complex conversational systems.
• Deep expertise with agentic orchestration frameworks and patterns (LangGraph, AutoGen, CrewAI; ReAct, CoT).
• Strong understanding of state management and session management for agentic workflows.
• Expert-level Python development skills, especially building REST APIs in Flask or FastAPI.
• Proficiency in deploying and managing AI workloads on AWS or GCP using containers (Docker, Kubernetes).
• Experience with evaluation methodologies for RAG and LLM applications.
• Experience using Vibe coding tools.

Good to have

• Experience with agent observability solutions.
• Understanding of classical AI techniques.
• End-to-end web application development experience.

Details

• Location: Sunnyvale, CA
• Job Function: Technology
• Role: Enterprise Architect
• Salary Range: $110,000 - $200,000 a year