Last reviewed 2025-11-10 UTC
This document in the Architecture Center provides links to architecture guides that you can use to build and deploy ML applications and operations in Google Cloud.
To help you find the right guidance that's relevant to your persona and needs, we provide the following types of architecture guides:
- Design guides: Prescriptive, cross-product guidance to help you plan and design your cloud architecture.
- Reference architectures: Detailed architecture examples and design recommendations for specific workloads.
- Use cases: High-level architecture examples to solve specific business problems.
- Deployment guides and Jump Start Solutions: Step-by-step instructions or code to deploy a specific architecture.
| Architecture guide | Description |
|---|---|
| Best practices for implementing machine learning on Google Cloud | A design guide to help you plan and develop custom-trained models that follow best practices throughout the ML workflow. |
| Guidelines for developing high-quality, predictive ML solutions | A guide that helps you assess, ensure, and control quality in building predictive ML solutions. |
| Architecture for MLOps using TensorFlow Extended, Vertex AI Pipelines, and Cloud Build | A reference architecture to help you build a machine learning (ML) system using TensorFlow Extended (TFX) libraries. |
| MLOps: Continuous delivery and automation pipelines in machine learning | A guide that discusses techniques for implementing and automating continuous integration (CI), continuous delivery (CD), and continuous training (CT) for ML systems. |
| Build an ML vision analytics solution with Dataflow and Cloud Vision API | A reference architecture to help you deploy a Dataflow pipeline to process image files with Cloud Vision and to store processed results in BigQuery. |
| Confidential computing for data analytics, AI, and federated learning | A reference architecture to help you use confidential computing for secure data collaboration, AI model training, and federated learning. |
| Cross-silo and cross-device federated learning on Google Cloud | A reference architecture to help you create a federated learning platform using Google Kubernetes Engine (GKE). |
| Implement two-tower retrieval for large-scale candidate generation | A reference architecture to help you implement an end-to-end two-tower candidate generation workflow with Vertex AI. |
| Model development and data labeling with Google Cloud and Labelbox | A reference architecture to help you build a standardized pipeline with Labelbox. |
| C3 AI architecture on Google Cloud | This document describes the most effective ways to deploy C3 AI applications. |
| Use Vertex AI Pipelines for propensity modeling on Google Cloud | A guide to help you deploy a pipeline implemented that performs propensity modeling. |