Google Cloud Platform LLM Agentic AI Solution Architect – Dice Job Posting

Job Title: Google Cloud Platform LLM Agentic AI Solution Architect
Location: Santa Clara, CA – Onsite
Experience: 10–12 Years

Position Overview

We are looking for an experienced LLM & Agentic AI Solution Architect to lead the architecture and delivery of enterprise-grade Generative AI and Agentic AI solutions across Azure and Google Cloud Platform environments.

The ideal candidate will have strong hands-on experience with Azure OpenAI, Azure AI Studio, Google Cloud Platform Vertex AI, LLM orchestration, RAG, LangChain/LangGraph, Kubernetes, cloud functions, APIs, and enterprise integrations.

Mandatory Skills

• Generative AI / LLM Solution Architecture – 2–3 years

• Agentic AI and Multi-Agent Architecture – 2–3 years

• RAG Architecture and Data Pipeline Design – 2–3 years

• LLM Orchestration using LangChain, LangGraph, AutoGen, or DSPy

• Azure OpenAI and Azure AI Studio – 2–3 years

• Google Cloud Platform Vertex AI – 2–3 years

• Python-based Microservices and Backend Architecture – 5 years

• Azure Functions / Google Cloud Platform Cloud Functions

• Kubernetes and Cloud-Native Architecture

• Enterprise APIs and Custom Connector Integrations

• API Management using Azure APIM, Apigee, or MuleSoft

• Vector Databases/Search – Azure Cognitive Search, Pinecone, Weaviate, FAISS, or Vertex AI Matching Engine

• LLM Fine-Tuning / PEFT – LoRA, QLoRA, PEFT

• LLM Memory Architecture – short-term, long-term, and episodic memory

• LLM Performance Optimization – latency, throughput, scalability

• LLM Governance, Security, Guardrails, and Responsible AI

Key Responsibilities

• Architect scalable and secure LLM and Agentic AI solutions across Azure and Google Cloud Platform.

• Design enterprise-grade RAG pipelines, AI assistants, and multi-agent applications.

• Lead architecture for LLM orchestration, tool invocation, context management, and task decomposition.

• Integrate Azure OpenAI, OpenAI, Google Cloud Platform Vertex AI, and third-party models into enterprise applications.

• Define API, microservices, cloud-function, Kubernetes, and integration architectures.

• Establish LLMOps/AgentOps practices including CI/CD, monitoring, observability, optimization, and cost management.

• Implement responsible AI controls including prompt-injection protection, content moderation, data protection, and hallucination mitigation.

• Lead architecture reviews, technical design authority, PoCs, and enterprise AI governance.

• Partner with engineering, data science, product, and business teams to translate AI use cases into production-ready solutions.

• Mentor engineering teams on LLM architecture, evaluation, performance tuning, and Agentic AI development.

Required Education

Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, or a related field.

Preferred / Secondary Skills

• MCP and A2A SDK knowledge

• Git / Version Control

• Agile / Scrum

• Jira / Azure DevOps

• BigQuery

• Azure Cognitive Services

• Azure Cognitive Search

• Google Cloud Platform Matching Engine

• LLM evaluation frameworks

• AI observability and AgentOps

What We’re Looking For

Candidates should demonstrate hands-on, project-level experience with the required technologies. Primary skills and exact years of experience should be clearly reflected in the resume, particularly across relevant projects.

Interested candidates can share their updated resume with