Section outline

• Select section Day 1: Introduction to MLOps

  Day 1: Introduction to MLOps

  Collapse all Expand all

  Module 1: Why & When Do We Need MLOps

  • ML engineering challenges and Google Cloud's role in MLOps
  • Differences between DevOps and MLOps
• Select section Day 2: Kubernetes and AI Platform Pipelines

  Day 2: Kubernetes and AI Platform Pipelines

  Module 2: Understanding the Main Kubernetes Components

  • Docker containers and Kubernetes architecture
  • Managing deployments with Google Kubernetes Engine

  Module 3: Introduction to AI Platform Pipelines

  • Setting up AI pipelines and configuring Google Kubernetes Engine
  • Connecting via Kubeflow Pipelines SDK
• Select section Day 3: Model Training, Tuning, and Serving

  Day 3: Model Training, Tuning, and Serving

  Module 4: Training, Tuning & Serving on AI Platform

  • Building and pushing training containers
  • Training, tuning, and serving models on AI Platform
• Select section Day 4: Advanced Pipelines and Deployment Strategies

  Day 4: Advanced Pipelines and Deployment Strategies

  Module 5: Kubeflow Pipelines on AI Platform

  • Using Kubeflow components and running pipeline builds

  Module 6: Kubernetes Deployment Strategy

  • Monitoring, liveness probes, and readiness probes
• Select section Day 5: CI/CD for ML Systems

  Day 5: CI/CD for ML Systems

  Module 7: CI/CD for Kubeflow Pipelines

  • Integrating CI/CD workflows with Kubeflow Pipelines