What is a key benefit of canary deployment?

It guarantees the new model is better

It eliminates the need for monitoring

It reduces the risk of deploying a faulty model to all users

A large enterprise has a complex serving pipeline that requires GPU acceleration, custom inference logic, and integration with existing Kubernetes-based monitoring. They want full control over the serving infrastructure. Which option is the best fit?

Deploy the model on GKE using a custom container and configure GPU node pools.

Deploy the model to Vertex AI Prediction with a custom container.

Use Vertex AI Batch Prediction with a custom container.

Use Cloud Run with GPU support and custom container.

What is a key characteristic of Cloud Run that makes it suitable for serving models?

It requires a Kubernetes cluster to be managed

It scales to zero when there is no traffic

It provides a built-in model registry

A team has a containerized model that returns raw logits. The application expects a class label and a confidence score. They want to deploy this on Cloud Run with minimal code changes. What is the best way to handle the output transformation?

Retrain the model to output class labels directly.

Modify the container's serving code to apply softmax and extract the class label and confidence before returning the response.

Use Vertex AI Prediction's built-in postprocessing features.

Have the client application apply softmax and determine the class label.

Google CloudProfessional Machine Learning Engineer

Domain 4Objective 1

Serving Models PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 1)

Part of the Serving and scaling models domain, which accounts for ~20% of the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam.

40questions here

8free pages

13concepts

~20%of the exam

Questions 1–5

1foundation · easy
What is a key benefit of canary deployment?
Select an answer first
2application · medium
A large enterprise has a complex serving pipeline that requires GPU acceleration, custom inference logic, and integration with existing Kubernetes-based monitoring. They want full control over the serving infrastructure. Which option is the best fit?
Select an answer first
3foundation · easy
What is a key characteristic of Cloud Run that makes it suitable for serving models?
Select an answer first
4application · medium
A team has a containerized model that returns raw logits. The application expects a class label and a confidence score. They want to deploy this on Cloud Run with minimal code changes. What is the best way to handle the output transformation?
Select an answer first
5foundation · easy
Which Google Cloud service provides Kubernetes orchestration for deploying models with custom serving infrastructure?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to PROFESSIONAL-MACHINE-LEARNING-ENGINEER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Google Cloud. “PROFESSIONAL-MACHINE-LEARNING-ENGINEER” is a trademark of its owner, used for identification only.