support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
CrowdStrike
Anthropic
All Vendors
  1. Home
  2. Exams
  3. Amazon
  4. AWS Certified Machine Learning Engineer - Associate MLA-C01

Free AWS Certified Machine Learning Engineer - Associate MLA-C01 Exam Braindumps
AWS Certified Machine Learning Engineer - Associate MLA-C01 Questions 97–104 (page: 14)

Updated On: 15-Apr-2026
Page 14 of 33
PDF with 270 Questions

A company uses 10 Reserved Instances of accelerated instance types to serve the current version of an ML model. An ML engineer needs to deploy a new version of the model to an Amazon SageMaker real-time inference endpoint.

The solution must use the original 10 instances to serve both versions of the model. The solution also must include one additional Reserved Instance that is available to use in the deployment process. The transition between versions must occur with no downtime or service interruptions.

Which solution will meet these requirements?

  1. Configure a blue/green deployment with all-at-once traffic shifting.
  2. Configure a blue/green deployment with canary traffic shifting and a size of 10%.
  3. Configure a shadow test with a traffic sampling percentage of 10%.
  4. Configure a rolling deployment with a rolling batch size of 1.

Answer(s): D

Explanation:

A rolling deployment updates instances gradually to ensure there is no downtime or service interruption. Since the company has 10 Reserved Instances serving the current model and one additional Reserved Instance available for deployment, a rolling batch size of 1 allows for updating one instance at a time while keeping the service available.
The rolling deployment replaces instances incrementally with the new model version.



At any time, at least 9 instances remain active with the original model, ensuring service availability.



The process continues until all instances have been updated with the new model.



An IoT company uses Amazon SageMaker to train and test an XGBoost model for object detection. ML engineers need to monitor performance metrics when they train the model with variants in hyperparameters. The ML engineers also need to send Short Message Service (SMS) text messages after training is complete.

Which solution will meet these requirements?

  1. Use Amazon CloudWatch to monitor performance metrics. Use Amazon Simple Queue Service (Amazon SQS) for message delivery.
  2. Use Amazon CloudWatch to monitor performance metrics. Use Amazon Simple Notification Service (Amazon SNS) for message delivery.
  3. Use AWS CloudTrail to monitor performance metrics. Use Amazon Simple Queue Service (Amazon SQS) for message delivery.
  4. Use AWS CloudTrail to monitor performance metrics. Use Amazon Simple Notification Service (Amazon SNS) for message delivery.

Answer(s): B

Explanation:

Amazon CloudWatch is the best choice for monitoring SageMaker performance metrics, including training loss, validation accuracy, and hyperparameter tuning performance. CloudWatch integrates with SageMaker to capture logs and metrics.
Amazon SNS is the best choice for sending SMS text messages upon training completion. SNS provides built-in support for sending notifications via SMS, email, or other messaging protocols, making it ideal for alerting ML engineers.



A company is working on an ML project that will include Amazon SageMaker notebook instances. An ML engineer must ensure that the SageMaker notebook instances do not allow root access.

Which solution will prevent the deployment of notebook instances that allow root access?

  1. Use IAM condition keys to stop deployments of SageMaker notebook instances that allow root access.
  2. Use AWS Key Management Service (AWS KMS) keys to stop deployments of SageMaker notebook instances that allow root access.
  3. Monitor resource creation by using Amazon EventBridge events. Create an AWS Lambda function that deletes all deployed SageMaker notebook instances that allow root access.
  4. Monitor resource creation by using AWS CloudFormation events. Create an AWS Lambda function that deletes all deployed SageMaker notebook instances that allow root access.

Answer(s): A

Explanation:

IAM condition keys allow you to enforce security policies by restricting actions based on specific attributes.
For SageMaker notebook instances, you can use IAM policies with condition keys to prevent the creation of notebook instances that allow root access.
sagemaker:RootAccess is an IAM condition key that can be set to "Disabled" to block the creation of notebook instances with root access.
This approach proactively prevents non-compliant resources from being deployed, instead of reactively deleting them like in other options.



A company is using Amazon SageMaker to develop ML models. The company stores sensitive training data in an Amazon S3 bucket. The model training must have network isolation from the internet.

Which solution will meet this requirement?

  1. Run the SageMaker training jobs in private subnets. Create a NAT gateway. Route traffic for training through the NAT gateway.
  2. Run the SageMaker training jobs in private subnets. Create an S3 gateway VPC endpoint. Route traffic for training through the S3 gateway VPC endpoint.
  3. Run the SageMaker training jobs in public subnets that have an attached security group. In the security group, use inbound rules to limit traffic from the internet. Encrypt SageMaker instance storage by using server-side encryption with AWS KMS keys (SSE-KMS).
  4. Encrypt traffic to Amazon S3 by using a bucket policy that includes a value of True for the aws:SecureTransport condition key. Use default at-rest encryption for Amazon S3. Encrypt SageMaker instance storage by using server-side encryption with AWS KMS keys (SSE-KMS).

Answer(s): B

Explanation:

To ensure network isolation from the internet, the best approach is to:
Run SageMaker training jobs in private subnets, which prevents direct internet access.



Use an Amazon S3 gateway VPC endpoint, which allows SageMaker instances to securely access training



data in Amazon S3 without using the internet.



A company needs an AWS solution that will automatically create versions of ML models as the models are created.

Which solution will meet this requirement?

  1. Amazon Elastic Container Registry (Amazon ECR)
  2. Model packages from Amazon SageMaker Marketplace
  3. Amazon SageMaker ML Lineage Tracking
  4. Amazon SageMaker Model Registry

Answer(s): D

Explanation:

Amazon SageMaker Model Registry is designed to automatically track and version ML models as they are created. It provides a centralized repository where you can manage different versions of ML models, their metadata, approval status, and deployment history.
With Model Registry, teams can:
Register new versions of models as they are trained.



Track metadata such as training configurations and performance metrics.



Manage model approvals before deployment.



Ensure a structured ML lifecycle with version control.



A company needs to use Retrieval Augmented Generation (RAG) to supplement an open source large language model (LLM) that runs on Amazon Bedrock. The company's data for RAG is a set of documents in an Amazon S3 bucket. The documents consist of .csv files and .docx files.

Which solution will meet these requirements with the LEAST operational overhead?

  1. Create a pipeline in Amazon SageMaker Pipelines to generate a new model. Call the new model from Amazon Bedrock to perform RAG queries.
  2. Convert the data into vectors. Store the data in an Amazon Neptune database. Connect the database to Amazon Bedrock. Call the Amazon Bedrock API to perform RAG queries.
  3. Fine-tune an existing LLM by using an AutoML job in Amazon SageMaker. Configure the S3 bucket as a data source for the AutoML job. Deploy the LLM to a SageMaker endpoint. Use the endpoint to perform RAG queries.
  4. Create a knowledge base for Amazon Bedrock. Configure a data source that references the S3 bucket.
    Use the Amazon Bedrock API to perform RAG queries.

Answer(s): D

Explanation:

The simplest and most efficient way to implement Retrieval Augmented Generation (RAG) with Amazon Bedrock and data stored in Amazon S3 is by using Amazon Bedrock Knowledge Bases. This service allows you to:
Connect structured and unstructured data sources, such as CSV and DOCX files stored in S3.



Automatically extract and index relevant information from documents.



Perform RAG queries efficiently by retrieving relevant context before generating responses.



Minimize operational overhead, since Bedrock manages the indexing and retrieval process natively.



A company plans to deploy an ML model for production inference on an Amazon SageMaker endpoint. The average inference payload size will vary from 100 MB to 300 MB. Inference requests must be processed in 60 minutes or less.

Which SageMaker inference option will meet these requirements?

  1. Serverless inference
  2. Asynchronous inference
  3. Real-time inference
  4. Batch transform

Answer(s): B

Explanation:

Amazon SageMaker Asynchronous Inference is the best choice for handling large inference payloads (100 MB to 300 MB) with response times of up to 60 minutes.
Handles large payloads: Unlike real-time inference, asynchronous inference supports larger payloads and



allows clients to send requests without waiting for an immediate response.

Longer processing time: It supports inference requests that take minutes to process, unlike real-time inference which is optimized for low-latency responses.
Efficient resource usage: Instances spin up only when needed, reducing costs compared to always-on endpoints.
Automatic output storage: The response is stored in Amazon S3, allowing retrieval when processing is complete.



An ML engineer notices class imbalance in an image classification training job.

What should the ML engineer do to resolve this issue?

  1. Reduce the size of the dataset.
  2. Transform some of the images in the dataset.
  3. Apply random oversampling on the dataset.
  4. Apply random data splitting on the dataset.

Answer(s): C

Explanation:

Class imbalance occurs when one class is significantly underrepresented compared to others, leading to a biased model that favors the majority class. Random oversampling is an effective technique to balance the dataset by increasing the number of instances in the minority class.
Oversampling works by duplicating or synthetically generating new samples of the minority class, helping the model learn features more effectively.
Alternative approaches include undersampling the majority class, using weighted loss functions, or employing data augmentation to artificially increase minority class samples.



  PDF
Viewing page 14 of 33
Viewing questions 105 - 112 out of 270 questions


Post your Comments and Discuss Amazon AWS Certified Machine Learning Engineer - Associate MLA-C01 exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!