Google - Professional Machine Learning Engineer certification

Curriculum

Section 1: ML Problem Framing

• Module 1: Translate business challenge into ML use case
• Module 2: Define ML problem
• Module 3: Define business success criteria
• Module 4: Identify risks to feasibility and implementation of ML solution

Section 2: ML Solution Architecture

• Module 1: Design reliable, scalable, highly available ML solutions
• Module 2: Choose appropriate Google Cloud software components
• Module 3: Choose appropriate Google Cloud hardware components
• Module 4: Design architecture that complies with regulatory and security concerns

Section 3: Data Preparation and Processing

• Module 1: Data ingestion
• Module 2: Data exploration (EDA)
• Module 3: Design data pipelines
• Module 4: Build data pipelines
• Module 5: Feature engineering

Section 4: ML Model Development

• Module 1: Build a model
• Module 2: Train a model
• Module 3: Test a model
• Module 4: Scale model training and serving

Section 5: ML Pipeline Automation & Orchestration

• Module 1: Design pipeline
• Module 2: Implement training pipeline
• Module 3: Implement serving pipeline
• Module 4: Track and audit metadata
• Module 5: Use CI/CD to test and deploy models

Section 6: ML Solution Monitoring, Optimization, and Maintenance

• Module 1: Monitor ML solutions
• Module 2: Troubleshoot ML solutions
• Module 3: Tune performance of ML solutions for training & serving in production