Gemini AI Architect-Governance Control Tower

 

This is the architectural owner role for the client''s Governance Control Tower — the single person who owns its design end to end and who platform leadership deals with directly. This person will define architecture standards and the checklist every agent must clear before going live, run the review board relationship, and lead a cross-functional delivery pod that implements and then operates the platform, staying hands-on through both a build phase (standing up the Control Tower) and a run phase (transitioning to a right-sized support pod while remaining the architectural owner). The role spans five workstreams: Governance & Standards, Registry & Gateway Operations, Connector & Retrieval Engineering, Identity & Entitlement Enforcement, and Observability & Cost Control.

Google Gemini Enterprise, Google ADK, Agent Registry, MCP, RAG, AI Governance, Identity & Entitlements, Observability & FinOps, Python

• Design the reusable top-level agent layer (orchestrator, context engineering, retrieval, synthesis, response) as the common entry point for every application on the platform

• Lead the delivery pod: set technical direction, review work, and be accountable for what ships

• Translate between platform leadership and the delivery team, turning direction into architecture and architecture into a defensible plan

• Hold the quality bar — evaluation datasets, threshold gates, and regression testing — so the platform stays reliable as agent count scales

• Own architecture across Governance & Standards, Registry & Gateway Operations, Connector & Retrieval Engineering, Identity & Entitlement Enforcement, and Observability & Cost Control

• 10+ years in software engineering and architecture, with 3+ years designing and running applied AI systems in production

• Proven experience as the architectural owner of an enterprise platform — set standards other teams had to follow, and made them stick

• Hands-on with Google Gemini Enterprise and ADK, or a directly comparable enterprise agent platform, including runtime, registration, identity, and observability

• Deep experience with multi-agent systems in production — orchestration, routing, tool use, memory, human-in-the-loop — with real operational ownership

• Strong grounding in RAG and retrieval architecture: vector stores, embedding models, chunking strategy, hybrid search

• Identity and access depth: OAuth2, SAML, RBAC, token exchange, service-account vs. end-user credential propagation, document-level ACL mapping into a retrieval layer

• Proficient in Python; comfortable with Go or an equivalent second language

• Experience with MCP — building servers, not only consuming them

• Solid cloud-native and systems fundamentals, Google Cloud Platform strongly preferred (Cloud Run, GKE, Vertex AI, networking, IAM)

• Cost awareness at scale — token and inference spend management across a growing agent estate