Gen AI Enterprise Architect

Role

This Enterprise Architect will design and deploy production-grade Generative AI and complex conversational systems, owning architecture for agentic workflows, evaluation, and cloud-based AI operations.

Key Responsibilities

• Architect and deploy agentic orchestration solutions using established frameworks and patterns.
• Design state management and session management for agentic workflows.
• Build and maintain REST APIs (Flask/FastAPI) for AI applications.
• Deploy and manage AI workloads on major cloud platforms using containers and orchestration tools.
• Integrate MCP components and develop MCP tool-layer capabilities.
• Define and apply evaluation methodologies for RAG and other LLM-powered applications.

Requirements

• Proven experience designing and deploying production-grade Generative AI and conversational systems.
• Deep expertise with agentic orchestration frameworks (LangGraph, AutoGen, CrewAI) and patterns (ReAct, CoT).
• Strong understanding of state management and session management for agentic workflows.
• Expert-level Python programming; experience building REST APIs with Flask or FastAPI.
• Proficiency in MLOps and deploying/managing AI workloads on cloud platforms (AWS or GCP) using Docker and Kubernetes.
• Experience with MCP integration and MCP tool-layer development.
• Knowledge of evaluation methodologies for RAG and other LLM applications.

Nice-to-have

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

Location & Compensation

• Location: Sunnyvale, CA
• Salary Range: $110,000 - $200,000 per year