EN简体繁體
Sign in
Home / Google / GCP-MLE
Google · GCP-MLE

GCP-MLE Exam Practice Questions

Google Professional Machine Learning Engineer

GCP-MLE English PDF practice questions: 375 questions in source order, with options supported by the source format, answers and available explanations. Access covers this exam only. One-time payment; no automatic renewal.

Exam overview

For ML engineers building, evaluating, deploying and monitoring models and production learning pipelines.

Exam code
GCP-MLE
Official exam / credential
Google Professional Machine Learning Engineer
Exam format
50–60 single-answer and multiple-select questions (standard exam)
Exam duration
120 minutes
Official exam languages
English, Japanese

Official exam languages and practice-question file languages are listed separately. Confirm the exam version and available languages when booking with the provider.

Official sources: Provider reference
Information checked: 2026-10-20

Supported languages

  • English
  • Simplified Chinese
Try before you buy

First 20 practice questions

375 total questions

Questions follow the source order. Expand each answer to see its explanation.

Disclaimer: All questions on ExamPico are compiled from internet sources and are provided for study reference only.

Question 6

Question#6Topic1

You work for an online retail company that is creating a visual search engine. You have set up an end-to-end ML pipeline on Google Cloud to classify whether an image contains your company's product. Expecting the release of new products in the near future, you configured a retraining functionality in the pipeline so that new data can be fed into your ML models. You also want to use AI Platform's continuous evaluation service to ensure that the models have high accuracy on your test dataset. What should you do?

  1. A. Keep the original test dataset unchanged even if newer products are incorporated into retraining.
  2. B. Extend your test dataset with images of the newer products when they are introduced to retraining.
  3. C. Replace your test dataset with images of the newer products when they are introduced to retraining.
  4. D. Update your test dataset with images of the newer products when your evaluation metrics drop below a pre-decided threshold.
Show answer and explanation

Answer

B

Explanation

A - Doesn't make sense. If you don't use the new product, it becomes useless. C - Conventional products are also necessary as data. D - I don't understand the need to wait until the threshold is exceeded.

Question 7

Question#7Topic1

You need to build classification workflows over several structured datasets currently stored in BigQuery. Because you will be performing the classification several times, you want to complete the following steps without writing code: exploratory data analysis, feature selection, model building, training, and hyperparameter tuning and serving. What should you do?

  1. A. Configure AutoML Tables to perform the classification task.
  2. B. Run a BigQuery ML task to perform logistic regression for the classification.
  3. C. Use AI Platform Notebooks to run the classification model with pandas library.
  4. D. Use AI Platform to run the classification model job configured for hyperparameter tuning.
Show answer and explanation

Answer

A

Explanation

Because BigQuery ML need to write code.

Question 8

Question#8Topic1

You work for a public transportation company and need to build a model to estimate delay times for multiple transportation routes. Predictions are served directly to users in an app in real time. Because different seasons and population increases impact the data relevance, you will retrain the model every month. You want to follow Google-recommended best practices. How should you configure the end-to-end architecture of the predictive model?

  1. A. Configure Kubeflow Pipelines to schedule your multi-step workflow from training to deploying your model.
  2. B. Use a model trained and deployed on BigQuery ML, and trigger retraining with the scheduled query feature in BigQuery.
  3. C. Write a Cloud Functions script that launches a training and deploying job on AI Platform that is triggered by Cloud Scheduler.
  4. D. Use Cloud Composer to programmatically schedule a Dataflow job that executes the workflow from training to deploying your model.
Show answer

Answer

A

Question 9

Question#9Topic1

You are developing ML models with AI Platform for image segmentation on CT scans. You frequently update your model architectures based on the newest available research papers, and have to rerun training on the same dataset to benchmark their performance. You want to minimize computation costs and manual intervention while having version control for your code. What should you do?

  1. A. Use Cloud Functions to identify changes to your code in Cloud Storage and trigger a retraining job.
  2. B. Use the gcloud command-line tool to submit training jobs on AI Platform when you update your code.
  3. C. Use Cloud Build linked with Cloud Source Repositories to trigger retraining when new code is pushed to the repository.
  4. D. Create an automated workflow in Cloud Composer that runs daily and looks for changes in code in Cloud Storage using a sensor.
Show answer and explanation

Answer

C

Explanation

CI/CD for Kubeflow pipelines. At the heart of this architecture is Cloud Build, infrastructure. Cloud Build can import source from Cloud Source Repositories, GitHub, or Bitbucket, and then execute a build to your specifications, and produce artifacts such as Docker containers or Python tar files.

Question 10

Question#10Topic1

Your team needs to build a model that predicts whether images contain a driver's license, passport, or credit card. The data engineering team already built the pipeline and generated a dataset composed of 10,000 images with driver's licenses, 1,000 images with passports, and 1,000 images with credit cards. You now have to train a model with the following label map: [`˜drivers_license', `˜passport', `˜credit_card']. Which loss function should you use?

  1. A. Categorical hinge
  2. B. Binary cross-entropy
  3. C. Categorical cross-entropy
  4. D. Sparse categorical cross-entropy
Show answer and explanation

Answer

C

Explanation

This loss function is commonly used for training neural networks when dealing with multiple classes. It measures the dissimilarity between predicted probabilities and true class labels, encouraging the model to assign high probabilities to the correct class and low probabilities to other classes. The categorical cross-entropy loss is well-suited for scenarios where each input image belongs to exactly one class out of several possible classes.

Downloads and personal use

  • Purchase this exam question set separately with 1, 3, 6 or 12 months of download access.
  • After payment confirmation, your library shows the download link and exact expiry time.
  • Download again during your term. Purchase a new term after expiry.
  • PDFs are licensed for personal study only and must not be resold or shared publicly.
  • Files already saved to your device are not remotely deleted when access expires.
How to choose your certification