Gemini AI Architect

InfiCare; San Ramon (CA); Hybrid; USD 180,000 - 260,000; Part time

Job summary

InfiCare is seeking a seasoned Gemini AI Architect to own the enterprise AI platform built on Google Gemini Enterprise and the Agent Platform. You will set standards for agent construction, governance, and operations across the organization, and ensure adoption at scale.

You will lead architecture across managed chat, enterprise search, agent gallery, and custom front-end apps, while enforcing identity, security, and cost governance in a hybrid onsite/work model in San Ramon.

Qualifications

• Architect large-scale AI platforms with enterprise-grade governance.
• Experience with Google Gemini Enterprise and ADK required.
• Strong understanding of identity, access, and RBAC.
• Proficiency in Python; familiarity with Go or similar.

Responsibilities

• Own the Gemini platform architecture and agent lifecycle.
• Govern the Agent Platform layer—ADK, runtime, registry, and security.
• Integrate data and identity layers across Workspace and 365.
• Enforce security, IAM, and auditing across services.
• Drive cost governance as the agent estate grows.

Skills

Multi-agent systems

RAG architecture

Identity & access

Python

Go

Tools

Google Gemini Enterprise

ADK

Google Cloud Platform

Docker

Kubernetes

Vertex AI

Job description

Job Title: Gemini AI Architect

Location: San Ramon, CA --- Hybrid (3 Days Onsite Weekly)

Job Type: Contract

Job Overview

Our client is seeking a seasoned Gemini AI Architect to serve as the architectural owner of an enterprise-scale AI platform built on Google Gemini Enterprise and the Agent Platform. You will set standards for how agents are built, governed, and operated across the organisation, and ensure those standards are adopted at scale.

Key Responsibilities

• Own the architecture of the enterprise Gemini platform including managed chat, enterprise search, agent gallery, and custom front-end applications
• Design and govern the Agent Platform layer --- ADK and agent runtime, agent and tool registry, agent identity, security, and observability
• Architect integration and data layers across Google Workspace, Microsoft 365, MCP servers, and federated retrieval across function‑scoped data stores
• Manage identity and access patterns including OAuth2, SAML, RBAC, token exchange, and document‑level ACL mapping into retrieval layers
• Drive cost awareness across token and inference spend as the agent estate grows
• Establish AI governance functions including review boards, architecture checklists, and audit evidence

Required Skills

• Google Gemini Enterprise and ADK (or comparable enterprise agent platform)
• Multi‑agent systems in production --- orchestration, routing, tool use, memory, human‑in‑the‑loop
• RAG architecture: vector stores, embedding models, chunking, hybrid search
• Identity and access: OAuth2, SAML, RBAC, token exchange, service‑account and end‑user credential propagation
• Python (proficient); Go or equivalent second language (comfortable)
• MCP --- building servers, not only consuming them
• Google Cloud Platform: Cloud Run, GKE, Vertex AI, networking, IAM

Preferred Skills

• Production deployment of agents on Gemini Enterprise / Agent Platform
• AI evaluation tooling: Langfuse, LangSmith, Braintrust, or custom eval frameworks
• Multi‑model routing across Gemini, Claude, OpenAI, or Llama
• Enterprise data connector work across Google Workspace and Microsoft 365
• AI governance experience inside regulated or multi‑entity enterprises
• Containerisation and orchestration: Docker, Kubernetes