Lead Agentic AI Developer - Google ADK Workflows

This role leads the design, architecture, and operationalization of enterprise-grade agentic AI systems spanning multiple orchestration frameworks - including Google’s Agent Development Kit (ADK), LangGraph, CrewAI, and AutoGen - deployed at scale on Google Cloud. Embedded within Clients AI engineering practice, the Lead Agentic AI Developer serves as the technical authority for agentic workflow design, framework selection, and cross-agent communication standards using MCP and A2A protocols. In the first 90 days, you will own the delivery of a production multi-agent system fully instrumented with evaluation, observability, and human-in-the-loop controls, integrated with enterprise data and API ecosystems., * Architect and lead delivery of production-grade multi-agent systems using Google ADK 2.0+, LangGraph, CrewAI, and AutoGen - selecting the right framework per workload based on compliance, auditability, and performance requirements.

• Design complex agentic workflows including branching logic, conditional execution, loop-based self-correction, and parallel fan-out patterns across Google Cloud and enterprise environments.
• Establish and enforce inter-agent communication standards using MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocols to enable seamless integration of heterogeneous agent ecosystems.
• Define human-in-the-loop controls, autonomy boundaries, and agent guardrail frameworks that ensure safe, compliant, and auditable behavior in regulated enterprise contexts.
• Build and maintain RAG and GraphRAG pipelines grounded in enterprise knowledge - including chunking strategies, hybrid vector search, and long-term agent memory management - to maximize factual accuracy and minimize hallucination.
• Deploy and operate agentic infrastructure on Google Cloud (Vertex AI, Cloud Run, Agent Engine) with high availability, security, and low-latency SLAs at scale.
• Create and industrialize automated evaluation frameworks that measure agent reasoning correctness, tool-use accuracy, latency, and business-outcome metrics across all deployed workflows.
• Mentor engineering teams, drive adoption of agentic best practices, and collaborate with product, AI research, and architecture stakeholders to define the enterprise agentic AI roadmap.

• 7+ years of experience in software engineering or AI/ML, with at least 3 years directly architecting and deploying production multi-agent or LLM-based systems at enterprise scale.
• Hands-on expertise across multiple agentic frameworks - including Google ADK, LangGraph, CrewAI, and/or AutoGen - with the ability to evaluate and select frameworks based on technical and business requirements.
• Deep proficiency in Python for production agentic development; strong command of prompt engineering, context management, and agentic design patterns (ReAct, Plan-and-Execute, state graphs).
• Demonstrated experience with Google Cloud Platform (Vertex AI, Cloud Run, BigQuery, Cloud Storage) and integration of agentic systems using MCP and A2A protocols.
• Strong background in RAG system design, vector store integration (Vertex AI Vector Search, Pinecone, Elasticsearch), and context engineering strategies including memory management and prompt compression.
• Bachelor’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.