Chapter 1 of 6 · Google Cloud Professional Machine Learning Engineer
Architecting low-code AI solutions
BigQuery ML, AutoML, Model Garden and Gemini.
- 4topics
- 21 minfast track
- 2diagrams and exhibits
- 13%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1BigQuery ML Models, Features and PredictionsChoose BigQuery ML model types for classification, regression, forecasting and clustering, engineer and select features in SQL…5 min
- 2AutoML Training and Tuning Gemini from BigQueryTrain AutoML models on Gemini Enterprise Agent Platform, choose between AutoML and BigQuery ML, and fine-tune Gemini models from…Diagram6 min
- 3Choosing Models in Model Garden and AI APIsSelect the right model from Model Garden and build applications with Document AI, Vision API, Translation API and other…5 min
- 4Building, Tuning and Optimizing Gemini ApplicationsBuild gen AI solutions with Gemini, Imagen, Veo and models as a service, decide when to tune, and optimize Gemini apps for cost…Diagram5 min
About this chapter
What this chapter covers
Architecting low-code AI solutions is about 13% of the Google Cloud Professional Machine Learning Engineer exam. It covers solving business problems with as little custom ML code as possible: training models in SQL with BigQuery ML, training with AutoML on Gemini Enterprise Agent Platform (the platform formerly called Vertex AI), and building on pretrained AI APIs and foundation models.
It covers BigQuery ML and AutoML (choosing classification, regression, forecasting or clustering for the business problem; feature engineering and selection; generating predictions; AutoML training; fine-tuning Gemini models from BigQuery) and AI APIs and foundation models (selecting a model in Model Garden; Document AI, Vision and Translation APIs; building and tuning with Gemini, Imagen, Veo and models as a service; optimizing Gemini applications for cost, latency and availability).
The exam has 50 to 60 multiple choice and multiple select questions in 2 hours. Questions in this section describe a business problem, where the data lives and what the team knows, and most end "What should you do?"; the best answer is usually the one with the least code and the least data movement.
How the topics fit together
Work left to right and stop at the first option that meets the requirement. Each step to the right adds control, but also cost, code and the skills the team needs.
"Data is already in BigQuery and the analysts know SQL" points to BigQuery ML. "No ML expertise, labeled tables or images, good accuracy with little effort" points to AutoML. "Extract fields from scanned invoices" points to Document AI, not a model you train yourself.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with tables and code examples.
- What to remember for the exam: the facts to memorise and how questions are phrased.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
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.
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.