Free study guide

Google Cloud Professional Machine Learning Engineer Study Guide

Google Cloud Certified - Professional Machine Learning Engineer

Google Cloud Professional Machine Learning Engineer is Google Cloud's professional-level certification for engineers who build, evaluate, productionize and optimize AI solutions, from conventional ML models to solutions based on foundation models. It covers low-code AI, managing data and models, training and scaling models, serving, ML pipelines and MLOps, and monitoring AI solutions with responsible AI practices. Google recommends 3 or more years of industry experience, including 1 or more years designing and managing solutions on Google Cloud.

  • Professional level
  • 6 exam sections
  • 50 to 60 questions

This guide is free, with no sign-up. It explains every Google Cloud Professional Machine Learning Engineer exam topic in plain English, one chapter at a time. Read them in order or jump straight to the topic you need.

  • 6chapters
  • 19topics
  • 6diagrams and exhibits
  • 1 h 38 minfast track
Start with Architecting low-code AI solutions
  • Every topic follows the same simple pattern: what it is, how it works, common mistakes
  • Diagrams and real command output where a picture explains it best
  • Exam tips and worked subnetting and IPv6 practice, with answers

How the exam is weighted

Each domain is worth this share of the exam, so spend your study time in proportion. Select a domain to open its chapter.

Chapters

Open a chapter to see its topics and how long each takes.

1Architecting low-code AI solutions4 topics · 21 min fast trackBigQuery ML, AutoML, Model Garden and Gemini.
  1. 1BigQuery ML Models, Features and Predictions5 min
  2. 2AutoML Training and Tuning Gemini from BigQuery6 min
  3. 3Choosing Models in Model Garden and AI APIs5 min
  4. 4Building, Tuning and Optimizing Gemini Applications5 min
Read the chapter overview →
2Collaborating within and across teams to manage data and models4 topics · 20 min fast trackPreprocessing, Feature Store, notebooks and experiment tracking.
  1. 1Organizing, Exploring and Preprocessing ML Data5 min
  2. 2Feature Store and Protecting Sensitive Data5 min
  3. 3Prototyping in Workbench and Colab Enterprise5 min
  4. 4Tracking Experiments, Evaluating Models and Lineage5 min
Read the chapter overview →
3Scaling prototypes into ML models4 topics · 20 min fast trackModel and product choice, training, tuning and hardware.
  1. 1Choosing the Model Type, Product and Deployment5 min
  2. 2Organizing Training Data and Running Training Jobs5 min
  3. 3Hyperparameter Tuning and Fine-Tuning Foundation Models5 min
  4. 4Training Hardware and Distributed Training5 min
Read the chapter overview →
4Serving and scaling models3 topics · 15 min fast trackBatch and online inference, Model Registry and scaling.
  1. 1Deploying Models for Batch and Online Inference5 min
  2. 2Model Registry Versions and Rollout Strategies5 min
  3. 3Scaling Online Serving with Endpoints and Features5 min
Read the chapter overview →
5Automating and orchestrating ML pipelines2 topics · 11 min fast trackPipelines, validation, retraining and CI/CD/CT.
  1. 1Building, Validating and Orchestrating ML Pipelines5 min
  2. 2Retraining Policies and CI/CD/CT Pipelines6 min
Read the chapter overview →
6Monitoring AI solutions2 topics · 11 min fast trackAI security, responsible AI, explainability, skew and drift.
  1. 1AI Security, Responsible AI and Explainability5 min
  2. 2Model Monitoring, Drift and Evaluating Gen AI6 min
Read the chapter overview →

Ready for more practice?

The full Google Cloud Professional Machine Learning Engineer question bank has 749 questions, with timed practice exams and an explanation for every answer.

SubscribeTry Sample Exam

This study guide is independent and is not affiliated with, endorsed by, or sponsored by Google Cloud. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.