An ML team is containerizing a custom inference service that will be deployed on Amazon ECS. They need to store the container image in a private registry and ensure that only authorized accounts can pull it. Which combination of actions should they take?

Use AWS Lambda layers to store the container image

Store the image in an S3 bucket and reference it from ECS

Push the image to Docker Hub and make it public

Create an Amazon ECR repository and configure a repository policy to allow specific accounts

AWSCertified Machine Learning Engineer - Associate

Domain 3Objective 2

Task 3.2: Create and Script Infrastructure Based on Existing Architecture and Requirements MLA-C01 Practice Questions (Page 5)

Part of the Content Domain 3: Deployment and Orchestration of ML Workflows domain, which accounts for 22% of the MLA-C01 exam. AWS does not publish an official question count, but from its 130-minute exam (~50–85 total, ~11–19 in this domain), expect 4–6 from this objective — we provide 33 practice questions to prepare you well beyond it. (estimate)

33questions here

7free pages

11concepts

22%of the exam

11 Concepts in This Objective

On-demand vs provisioned resources
Scaling policy comparison
Infrastructure as code options
Containerization fundamentals
SageMaker endpoint auto scaling
Best practices for ML solutions
Automating compute provisioning
Building and maintaining containers
SageMaker endpoints in VPC
Deploying models with SageMaker SDK
Auto scaling metrics selection

Questions 21–25

21application · medium
An ML team is containerizing a custom inference service that will be deployed on Amazon ECS. They need to store the container image in a private registry and ensure that only authorized accounts can pull it. Which combination of actions should they take?
Select an answer first
22expert · hard
A startup runs a batch inference job that processes a large dataset every night. The job is fault-tolerant and can be interrupted. They want to minimize costs while ensuring the job completes within a few hours. Which compute option should they use?
Select an answer first
23foundation · easy
Which SageMaker AI SDK method is used to deploy a trained model to a real-time endpoint?
Select an answer first
24foundation · easy
Which scaling policy is best suited for a workload with predictable, recurring traffic spikes at the same time each day?
Select an answer first
25foundation · easy
Which AWS service is used to automatically adjust the number of instances for a SageMaker AI endpoint based on demand?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MLA-C01

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 AWS. “MLA-C01” is a trademark of its owner, used for identification only.

Task 3.2: Create and Script Infrastructure Based on Existing Architecture and Requirements MLA-C01 Practice Questions (Page 5)

Questions 21–25

An ML team is containerizing a custom inference service that will be deployed on Amazon ECS. They need to store the container image in a private registry and ensure that only authorized accounts can pull it. Which combination of actions should they take?

A startup runs a batch inference job that processes a large dataset every night. The job is fault-tolerant and can be interrupted. They want to minimize costs while ensuring the job completes within a few hours. Which compute option should they use?

Which SageMaker AI SDK method is used to deploy a trained model to a real-time endpoint?

Which scaling policy is best suited for a workload with predictable, recurring traffic spikes at the same time each day?

Which AWS service is used to automatically adjust the number of instances for a SageMaker AI endpoint based on demand?

Keep studying — Content Domain 3: Deployment and Orchestration of ML Workflows