This cloud-native training course introduces data scientists to Google Cloud Platform (GCP) tools for scalable data science and machine learning. Participants will learn how to work with BigQuery for data analysis, and build, train, and deploy models using Vertex AI. This professional course combines SQL, AutoML, and custom modeling workflows, ideal for teams transitioning to GCP or scaling their ML operations.
Hands-on labs in Google Cloud Console and Vertex AI
Code-along notebooks using BigQuery and Vertex Pipelines
Real datasets from marketing, retail, or finance
Capstone project integrating full ML lifecycle on GCP
Navigate key GCP services for data science and ML
Use BigQuery for large-scale data exploration and feature engineering
Build ML models using Vertex AI Workbench
Train and deploy models using custom or AutoML workflows
Automate and manage end-to-end ML pipelines with Vertex Pipelines
Ensure model reproducibility, monitoring, and version control
Apply GCP best practices for performance, cost, and security
Day 1
Session 1: Introduction to Data Science on GCP
Overview of GCP services for data and ML
BigQuery, Vertex AI, Cloud Storage, and Notebooks
Navigating the Google Cloud Console
Session 2: Data Exploration in BigQuery
Loading structured/unstructured data
Writing efficient SQL for analysis
Data joins, filters, and transformations
Day 2
Session 3: Feature Engineering in BigQuery
Creating derived variables and aggregates
Using user-defined functions (UDFs)
Exporting data to Vertex AI
Session 4: Introduction to Vertex AI
Overview of Vertex AI Workbench and datasets
Using prebuilt models and AutoML
Training and evaluating models
Day 3
Session 5: Custom Model Training and Deployment
Writing custom training code with TensorFlow/Scikit-learn
Training in Notebooks or using containers
Deploying models as endpoints
Session 6: Vertex AI Pipelines and Workflow Automation
Setting up reusable ML workflows
Artifact tracking, metadata, and reproducibility
Running batch jobs and real-time predictions
Day 4
Session 7: Monitoring and Model Management
Model versioning and rollback
Bias detection and explainability tools
GCP security and IAM roles for ML
Session 8: Use Case Simulation: Customer Segmentation or Demand Forecasting
Build a complete pipeline
Ingest, train, deploy, and evaluate
Day 5
Session 9: Final Project – Full ML Lifecycle on GCP
Solve a business challenge from start to finish
Present architecture, model output, and impact
Session 10: Review and Next Steps
Vertex AI vs SageMaker vs Azure ML
GCP certification tracks and best practices
Team roadmap for production ML on GCP
We are open to customizing this program to align with your specific learning objectives. If your team has particular goals or areas they wish to focus on, we would be happy to tailor the course outline to meet those needs and ensure the program supports the achievement of your desired outcomes.
