MLS-C01 Practice Test 31 — 15 Questions

Question 1

A data scientist is training a model using Amazon SageMaker. The training dataset is 500 GB and is stored in S3. The data scientist wants to use Pipe input mode to stream data directly from S3 to the training container. However, the training job fails with an error indicating that the container cannot read the data. What is the most likely cause?

Accepted Answer

The training algorithm does not support Pipe mode. Option D is correct because Pipe mode requires the training algorithm to support reading from a FIFO pipe (e.g., via stdin) rather than random access files. Option A (S3 bucket) is accessible. Option B (instance type) is not specific to Pipe mode. Option C (IAM role) is needed but if permissions are correct, the issue is algorithm support. Option E (compression) is not a problem for Pipe mode.

Answer

The training instance does not have enough memory

Answer

The IAM role does not have s3:GetObject permission

Answer

The data is compressed and Pipe mode cannot handle compressed data

Answer

The S3 bucket is in a different Region

Question 2

A data scientist is training a TensorFlow model on a single GPU instance. The training is taking too long. Which AWS service should be used to reduce training time by distributing the workload across multiple GPUs?

Accepted Answer

Amazon SageMaker. Amazon SageMaker supports distributed training across multiple GPUs using the SageMaker distributed training libraries. Option B is correct. Option A is wrong because AWS Batch is for batch computing, not specifically optimized for GPU training. Option C is wrong because Amazon EMR is for big data processing. Option D is wrong because AWS Glue is for ETL jobs.

Answer

AWS Glue

Answer

Amazon EMR

Answer

AWS Batch

Question 3

A machine learning engineer is deploying a real-time inference endpoint using Amazon SageMaker. The model is a large deep learning model that requires low latency (under 100 ms) and high throughput (1000 requests per second). Which SageMaker deployment option is MOST suitable?

Accepted Answer

Use SageMaker Inference Recommender to find the optimal instance type and endpoint configuration.. Option C is correct because SageMaker Inference Recommender provides automated testing and recommendations for instance type and configuration to meet latency and throughput requirements. Option A is wrong because Multi-Model Endpoints are designed for multiple small models, not optimized for a single large model's throughput. Option B is wrong because Serverless Inference has a maximum concurrency and may not achieve 1000 TPS with low latency. Option D is wrong because a single endpoint may not handle the load; Auto Scaling helps but does not guarantee optimal instance choice.

Answer

Deploy the model on a single endpoint with automatic scaling based on CPU utilization.

Answer

Use SageMaker Serverless Inference with provisioned concurrency.

Answer

Use a multi-model endpoint to load multiple copies of the model on the same instance.

Question 4

Refer to the exhibit. A company is using an IAM role with the attached policy to deploy a SageMaker model. The data scientist can create training jobs and models, but when trying to create an endpoint, they receive an access denied error. What is the missing permission?

Accepted Answer

ec2:CreateNetworkInterface. Option E is correct because to create an endpoint, SageMaker needs permission to call ec2:CreateNetworkInterface to set up the elastic network interface in the customer's VPC. Option A (sagemaker:InvokeEndpoint) is for invoking, not creating. Option B (iam:PassRole) is needed to pass the execution role to SageMaker, but the error is about creating endpoint, not passing role. Option C (kms:Decrypt) is for encrypted data. Option D (cloudwatch:PutMetricData) is for publishing metrics.

Answer

cloudwatch:PutMetricData

Answer

iam:PassRole

Answer

sagemaker:InvokeEndpoint

Answer

kms:Decrypt

Question 5

A company is deploying a real-time inference endpoint using SageMaker. The model has a high memory footprint and requires GPU acceleration. Which instance type and configuration should be used to minimize cost while meeting latency requirements?

Accepted Answer

ml.p3.2xlarge with 1 GPU. Option C is correct because the p3.2xlarge provides GPU acceleration with sufficient memory for a high-memory model and is cost-effective for real-time inference. Option A is incorrect because ml.c5.xlarge does not have GPU. Option B is incorrect because p3.16xlarge is too large and expensive. Option D is incorrect because ml.g4dn.xlarge has less memory and may not be suitable for high memory footprint.

Answer

ml.g4dn.xlarge with 1 GPU

Answer

ml.c5.xlarge with no GPU

Answer

ml.p3.16xlarge with 8 GPUs

Question 6

A machine learning engineer needs to deploy a model that requires custom inference code with dependencies. Which SageMaker deployment option should be used?

Accepted Answer

Create a custom Docker container and deploy to SageMaker endpoint.. Option A is correct because a custom container allows full control over dependencies and inference code. Option B is incorrect because a built-in algorithm may not support custom code. Option C is incorrect because a SageMaker notebook instance is for development, not deployment. Option D is incorrect because a batch transform job is for batch inference, not real-time.

Answer

Use a SageMaker notebook instance as an endpoint.

Answer

Use a built-in SageMaker algorithm.

Answer

Use a SageMaker batch transform job.

Question 7

A company is building a recommendation system using Amazon SageMaker. The training data includes user-item interactions stored in a DataFrame with over 100 million rows. The data scientist wants to perform feature engineering, including one-hot encoding of categorical features with high cardinality. Which approach is MOST cost-effective and scalable?

Accepted Answer

Use SageMaker Processing with a Spark container to distribute the encoding job.. Option B is correct because SageMaker Processing with a Spark job can scale horizontally and is cost-effective for large datasets. Option A is wrong because scikit-learn on a single instance may not handle 100M rows. Option C is wrong because Glue is serverless but may be more expensive for large processing. Option D is wrong because EMR is more complex and costly for a simple job.

Answer

Use Amazon EMR with Spark and store the processed data in HDFS.

Answer

Use a SageMaker notebook instance with scikit-learn to perform the encoding in memory.

Answer

Use AWS Glue ETL jobs to perform the encoding and store the result in S3.

Question 8

An ML team is using SageMaker Processing jobs to run feature engineering scripts. The scripts require a specific Python package not included in the default SageMaker image. How should the team provide this package?

Accepted Answer

Create a custom Docker image that includes the package and use it for the Processing job. A custom container allows full control over dependencies. Option A is wrong because pip install in script is not persisted. Option B is wrong because SageMaker doesn't support requirements.txt directly. Option D is wrong because a prebuilt image may not have the package.

Answer

Include 'pip install <package>' in the processing script

Answer

Use the SageMaker prebuilt deep learning container with the package

Answer

Place a requirements.txt file in the input data S3 bucket

Question 9

A data scientist is using Amazon SageMaker to train a model. The training job is taking longer than expected. The data scientist notices that the GPU utilization is low. Which action would most likely improve GPU utilization?

Accepted Answer

Increase the batch size. Option A is correct because increasing the batch size allows the GPU to process more data per step, improving utilization. Option B (reduce batch size) would decrease utilization. Option C (increase instance type) may help but is more costly. Option D (enable data augmentation) increases data, not utilization. Option E (use CPU instance) would make it worse.

Answer

Change to a CPU-based instance

Answer

Decrease the batch size

Answer

Use a larger instance type

Answer

Enable data augmentation

Question 10

Which TWO AWS services can be used to deploy a trained model for serverless inference? (Select TWO.)

Accepted Answer

AWS Lambda with a container image. SageMaker Serverless Inference automatically scales. Lambda can serve models if they fit within its limits. Option C is wrong because SageMaker batch transform is not serverless real-time. Option D is wrong because ECS is not serverless (requires management). Option E is wrong because EC2 is not serverless.

Answer

Amazon SageMaker batch transform

Answer

Amazon Elastic Container Service (ECS) with Fargate

Answer

Amazon EC2 instances

Question 11

A company is using Amazon SageMaker to deploy a model. The model is a large ensemble that requires 8 GB of memory. The company wants to minimize endpoint cost. Which instance type should they choose?

Accepted Answer

ml.c5.xlarge. Option B is correct because ml.c5.xlarge has 8 GB memory, sufficient for the model. Option A (ml.c5.large) has 4 GB, not enough. Option C (ml.c5.2xlarge) has 16 GB, over-provisioned. Option D (ml.m5.large) has 8 GB but is more expensive than c5. Option E (ml.t2.medium) has 4 GB.

Answer

ml.m5.large

Answer

ml.t2.medium

Answer

ml.c5.large

Answer

ml.c5.2xlarge

Question 12

A company is deploying a machine learning model to production on Amazon SageMaker. The model requires low-latency inference (under 10 ms) for real-time predictions. The data scientist has trained a model using XGBoost and wants to minimize cost while meeting latency requirements. Which SageMaker hosting option should be used?

Accepted Answer

Use a real-time endpoint with a single model. Option B is correct because SageMaker real-time endpoints provide low-latency inference suitable for real-time predictions. Option A (batch transform) is for offline predictions, not real-time. Option C (serverless inference) has cold starts and may not guarantee under 10 ms. Option D (asynchronous inference) is for near-real-time with higher latency. Option E (multi-model endpoint) can reduce cost by sharing resources, but may introduce higher latency due to model loading.

Answer

Use a serverless inference endpoint

Answer

Use a real-time endpoint with multi-model hosting

Answer

Use a batch transform job

Answer

Use an asynchronous inference endpoint

Question 13

Refer to the exhibit. A data scientist is reviewing CloudWatch logs for a SageMaker real-time endpoint. The log shows that a prediction took 15 ms. The endpoint is configured with an ml.c5.large instance and the model is a small scikit-learn model. The latency requirement is under 10 ms. Which action would most likely reduce the latency?

Accepted Answer

Use a larger instance type. Option D is correct because using a larger instance (ml.c5.xlarge) provides more CPU resources, reducing inference time. Option A (increase batch size) is not applicable for real-time single requests. Option B (enable SageMaker Batch Transform) is for offline. Option C (add more instances) does not reduce per-request latency. Option E (use a different framework) is not likely the issue.

Answer

Add more instances to the endpoint

Answer

Change the model to a TensorFlow model

Answer

Enable SageMaker Batch Transform

Answer

Increase the batch size for inference

Question 14

A company is building a machine learning pipeline on AWS. The pipeline includes data ingestion, preprocessing, training, and deployment. Which THREE AWS services can be used to orchestrate the pipeline? (Choose THREE.)

Accepted Answer

AWS Glue Workflows. Option A, B, and C are correct because Step Functions, SageMaker Pipelines, and AWS Glue Workflows provide orchestration capabilities. Option D is wrong because Lambda is a compute service, not a workflow orchestrator. Option E is wrong because CloudWatch is for monitoring.

Answer

Amazon CloudWatch

Answer

AWS Lambda

Question 15

A team is training a large language model using PyTorch on multiple GPUs. The training is taking too long due to inefficient data loading. Which AWS service can help accelerate data loading by caching data close to the GPU instances?

Accepted Answer

Amazon FSx for Lustre. Amazon EBS Snapshots are not for caching. FSx for Lustre provides high-performance file system optimized for ML workloads. Option B is wrong because S3 Transfer Acceleration speeds up uploads, not loading. Option D is wrong because CloudFront is a CDN for web content.

Answer

Amazon EBS Snapshots for fast restore

Answer

Amazon S3 Transfer Acceleration

Answer

Amazon CloudFront