About the Exam

Validates the ability to build, operationalize, deploy, and maintain machine learning solutions and pipelines on AWS. It is intended for people in ML engineering and related technical roles, including data engineers, MLOps engineers, DevOps engineers, backend developers, and data scientists, with hands-on AWS experience. Passing demonstrates technical skill in implementing ML solutions on AWS and managing the associated workflows and infrastructure.

Exam Topics

  • Data Preparation for Machine Learning (ML)28%
  • ML Model Development26%
  • Deployment and Orchestration of ML Workflows22%
  • ML Solution Monitoring, Maintenance, and Security24%

How to Use This Practice Exam

  1. Browse — Read each question, select your answer, and reveal the explanation.
  2. Exam Mode — Simulate real exam conditions with a timed session and score report.
  3. Learn Mode — Spaced repetition schedules questions you struggle with for long-term retention.

Download the Full Exam PDF

Get every question and answer in a clean, printable PDF built for offline study. Purchase once, keep permanent access, and re-download the latest version anytime.

Last updated June 30, 2026 at 9:22 PM

Topic filter
Question status
Question sort
Questions per page

QuestionQ1

VerifiedML Model Development

A company operates a neural network model and retrains it when its performance declines. The company uses a training job that uses Amazon SageMaker AI distributed data parallelism (DDP). The training job requires several hours to complete.

The company wants to reduce the time required for the training job.

Which solution will satisfy this requirement?

Explanation

Amazon SageMaker AI distributed data parallelism distributes training work across GPUs and instances. Increasing the number of instances increases the training cluster size and available parallel compute capacity, which can reduce wall-clock training time. More epochs or a larger/deeper network instead increase the amount of training computation.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ2

VerifiedDeployment and Orchestration of ML Workflows

A company has trained an ML model that is packaged in a container. The company will integrate this model with an existing Python web application. The company needs to host the model on AWS using Kubernetes.

The company does not want to manage the control plane and must provision resources repeatably. The infrastructure must be provisioned using Python.

Which solution meets these requirements?

Explanation

Amazon EKS provides a managed Kubernetes control plane, so the company does not operate that control-plane infrastructure. AWS CDK supports defining EKS infrastructure in Python, providing repeatable infrastructure-as-code deployment; the container image can be stored in Amazon ECR and run as a workload on EKS.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ3

VerifiedData Preparation for Machine Learning (ML)

A company plans to use Amazon SageMaker to produce image-based classification ratings. The company has 6 ТВ of training data stored on an Amazon FSx for NetApp ONTAP storage virtual machine (SVM). The SVM is in the same VPC as SageMaker.

An ML engineer must make the training data available to ML models in the SageMaker environment.

Which solution meets these requirements?

Explanation

Amazon FSx for NetApp ONTAP SVMs provide NFS endpoints for data access. Mounting the ONTAP file system on a SageMaker instance in the same VPC gives the ML environment direct access to the existing training files without copying the 6 ТВ dataset or using an unsupported Data Wrangler connection type.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ4

VerifiedData Preparation for Machine Learning (ML)

An ML engineer is developing a logistic regression model to predict customer churn for subscription services. The ML engineer is using a dataset that includes two string variables: location and job_seniority_level. The location variable has 3 distinct values, while the job_seniority_level variable has more than 10 distinct values.

The ML engineer must preprocess these variables.

Which solution meets this requirement?

Explanation

One-hot encoding is appropriate for location because its categories are nominal and should not be assigned an artificial order. Ordinal encoding is appropriate for job_seniority_level because seniority levels have an inherent order. Categorical string values must be converted to numeric representations for use as logistic-regression features; standard scaling and binning are not categorical encoders.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ5

VerifiedDeployment and Orchestration of ML Workflows

A company plans to build several ML prediction models. Its training data is stored in Amazon S3. The complete dataset is more than 5 ТВ in size and contains CSV, JSON, Apache Parquet, and simple text files.

The data must be processed through several consecutive steps. These steps include complex manipulations that can require hours to complete. Some processing includes natural language processing (NLP) transformations. The entire process must be automated.

Which solution meets these requirements?

Explanation

Amazon SageMaker Pipelines orchestrates interconnected, dependency-based ML workflow steps and can include SageMaker processing jobs for large-scale, long-running custom data transformations such as NLP. Amazon EventBridge can automatically initiate a pipeline execution, including in response to events such as new objects in an S3 bucket. AWS Lambda is unsuitable for transformations that run for hours because a Lambda invocation has a maximum execution time of 15 minutes.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!
Know a question that should be here? Contribute to this exam
Back home