A company has an application that uses different APIs to generate embeddings for input text. The company needs to implement a solution to automatically rotate the API tokens every 3 months.
Which solution will meet this requirement?
A. Store the tokens in AWS Secrets Manager. Create an AWS Lambda function to perform the rotation.
B. Store the tokens in AWS Systems Manager Parameter Store. Create an AWS Lambda function to perform the rotation.
C. Store the tokens in AWS Key Management Service (AWS KMS). Use an AWS managed key to perform the rotation.
D. Store the tokens in AWS Key Management Service (AWS KMS). Use an AWS owned key to perform the rotation.
Show Answer
Correct Answer: A
Explanation: AWS Secrets Manager is designed to store credentials and supports scheduled rotation using a Lambda function. A custom Lambda can rotate the external API tokens every three months. Parameter Store does not provide the same built-in rotation workflow, and KMS manages encryption keys rather than API tokens.
Question 8
An ML engineer is importing a custom model from the Hugging Face Hub into Amazon Bedrock. The ML engineer wants to use the model with the Amazon Bedrock API in an agentic AI application.
Which combination of steps will meet these requirements? (Choose two.)
A. Import the model for deployment by using Amazon Bedrock On-Demand mode.
B. Convert the model to a quantized format. Import the quantized model after conversion.
C. Import the model directly by using the Amazon SageMaker AI SDK in the agentic AI application.
D. During the model import process, configure an auto-scaling policy before using the model in the agentic AI application.
E. In the import job, provide the complete Amazon S3 URI that points to the Hugging Face model files. Ensure that the S3 URI is in the same AWS account as the Amazon Bedrock import job.
Show Answer
Correct Answer: A, E
Explanation: Amazon Bedrock custom model import supports importing model artifacts from Amazon S3 and then deploying the imported model for inference through the Bedrock API using On-Demand inference. The import job requires the full S3 URI for the model artifacts in the same AWS account. Quantization is not a required import step, SageMaker SDK is not used to import models into Bedrock for Bedrock API use, and auto-scaling is not configured during the import job.
Question 8
An ecommerce company trains an ML model to forecast demand for near real-time inventory management based on historical customer activity. The company successfully deploys the trained model to a production Amazon SageMaker AI endpoint. However, the company notices that the model’s forecast performance degrades over time. The company needs a long-term and automated solution to mitigate the performance degradation.
Which solution will meet these requirements?
A. Use Amazon SageMaker Debugger to automatically send alerts when model performance anomalies are detected.
B. Use AWS X-Ray to monitor the performance of the SageMaker AI endpoint and the incoming requests to inform model re-training.
C. Use Amazon SageMaker Ground Truth to curate a high-quality dataset. Use the dataset to re-train the model.
D. Use Amazon SageMaker Clarify to monitor model and feature attribution bias to inform model re-training.
Show Answer
Correct Answer: D
Explanation: Amazon SageMaker Clarify can monitor production data for changes in bias and feature attributions, helping identify shifts that may contribute to degrading forecasts and inform retraining. Debugger focuses on model training and debugging, X-Ray traces application requests, and Ground Truth helps create labeled datasets rather than continuously monitoring a deployed model.
Question 8
A company has an ML model that needs to run one time each night to predict stock values. The model input is 3 MB of data that is collected during the current day. The model produces the predictions for the next day. The prediction process takes less than 1 minute to finish running.
How should the company deploy the model on Amazon SageMaker to meet these requirements?
A. Use a multi-model serverless endpoint. Enable caching.
B. Use an asynchronous inference endpoint. Set the InitialInstanceCount parameter to 0.
C. Use a real-time endpoint. Configure an auto scaling policy to scale the model to 0 when the model is not in use.
D. Use a serverless inference endpoint. Set the MaxConcurrency parameter to 1.
Show Answer
Correct Answer: D
Explanation: Use a serverless inference endpoint for the once-nightly, low-volume workload. The 3 MB input is within the serverless request-size limit, and a prediction completing in under one minute fits its execution-time limit. Setting MaxConcurrency to 1 is sufficient for the single nightly invocation and avoids provisioning instances between runs.
Question 9
A digital media entertainment company needs real-time video content moderation to ensure compliance during live streaming events.
Which solution will meet these requirements with the LEAST operational overhead?
A. Use Amazon Rekognition and AWS Lambda to extract and analyze the metadata from the videos’ image frames.
B. Use Amazon Rekognition and a large language model (LLM) hosted on Amazon Bedrock to extract and analyze the metadata from the videos’ image frames.
C. Use Amazon SageMaker AI to extract and analyze the metadata from the videos’ image frames.
D. Use Amazon Transcribe and Amazon Comprehend to extract and analyze the metadata from the videos’ image frames.
Show Answer
Correct Answer: A
Explanation: Amazon Rekognition provides managed image and video analysis, including content moderation capabilities suitable for near real-time processing. AWS Lambda can orchestrate serverless extraction and analysis of video frames with minimal operational overhead. SageMaker requires managing ML deployments, Bedrock LLMs are not the appropriate primary service for visual moderation, and Transcribe plus Comprehend analyze speech/text rather than image frames.
Question 9
An ML engineer needs to train a supervised deep learning model. The available dataset is a large number of unlabeled images that only employees should access. The ML engineer needs to implement a solution that labels the dataset with the highest possible accuracy.
Which combination of steps should the ML engineer take to meet these requirements? (Choose two.)
A. Use Amazon Rekognition to automatically label the dataset.
B. Train the deep learning model directly on the raw data. Let the model infer the labels by itself.
C. Use Amazon SageMaker Ground Truth to create an annotation job that specifies the labeling task and requirements.
D. Set up workforce teams to access a private workforce to run and review the annotation job created by Amazon SageMaker Ground Truth.
E. Use Amazon Mechanical Turk to complete the annotation job created by Amazon SageMaker Ground Truth.
Show Answer
Correct Answer: C, D
Explanation: Amazon SageMaker Ground Truth creates the annotation job and defines the labeling task. A private workforce lets the organization’s employees perform and review the labeling, keeping access restricted while supporting accurate human annotations. Mechanical Turk uses an external crowd, and training directly on unlabeled images does not provide the labels needed for supervised learning.
Question 9
An ML engineer is training a simple neural network model. The ML engineer tracks the performance of the model over time on a validation dataset. The model's performance improves substantially at first and then degrades after a specific number of epochs.
Which solutions will mitigate this problem? (Choose two.)
A. Enable early stopping on the model.
B. Increase dropout in the layers.
C. Increase the number of layers.
D. Increase the number of neurons.
E. Investigate and reduce the sources of model bias.
Show Answer
Correct Answer: A, B
Explanation: The model is likely overfitting: validation performance improves initially, then worsens as training continues. Early stopping halts training when validation performance stops improving, and dropout helps reduce overfitting by regularizing the network.
Question 10
An ML engineer has an Amazon Comprehend custom model in Account A in the us-east-1 Region. The ML engineer needs to copy the model to Account В in the same Region.
Which solution will meet this requirement with the LEAST development effort?
A. Use Amazon S3 to make a copy of the model. Transfer the copy to Account B.
B. Create a resource-based IAM policy. Use the Amazon Comprehend ImportModel API operation to copy the model to Account
C. Use AWS DataSync to replicate the model from Account A to Account B.
D. Create an AWS Site-to-Site VPN connection between Account A and Account В to transfer the model.
Show Answer
Correct Answer: B
Explanation: Create a resource-based policy on the custom model in Account A to grant Account B access, then use Amazon Comprehend’s ImportModel API in Account B. This is the service-supported way to copy a custom model across accounts in the same Region, with less effort than manually transferring model files or setting up data-transfer infrastructure.
Question 11
An ML engineer is designing an AI-powered traffic management system to adjust traffic lights during predicted congestion. The system must use near real-time inference to generate predictions to help prevent traffic collisions. The system must use a batch processing pipeline to perform historical analysis of the predictions to continuously refine and improve the model. The historical analysis will take several hours to evaluate how well the predictions correlate with actual outcomes. The system must be able to scale inference endpoints appropriately to meet demand.
Which combination of solutions will meet these requirements? (Choose two.)
A. Use Amazon SageMaker real-time inference endpoints. Configure the endpoints to scale automatically based on a target tracking scaling policy that uses the metric ConcurrentInvocationsPerinstance.
B. Configure reserved concurrency for AWS Lambda functions to process streaming data. Use Lambda SnapStart to connect the Lambda functions to Amazon SageMaker real-time endpoints to support near real-time traffic predictions.
C. Configure an Amazon SageMaker Processing job for batch analysis of historical prediction data. Use Amazon EventBridge to schedule the job to run daily. Allow several hours for in-depth analysis to refine and improve the traffic management model.
D. Use an Amazon EC2 Auto Scaling group to host containers to support the batch analysis of historical prediction data. Configure scaling based on Amazon CloudWatch metrics to analyze historical traffic patterns and model performance over multiple hours.
E. Use an AWS Lambda function to perform the historical analysis. Use Amazon EventBridge to invoke the Lambda function.
Show Answer
Correct Answer: A, C
Explanation: Near real-time inference with automatic scaling is best handled by Amazon SageMaker real-time inference endpoints with target tracking auto scaling using the ConcurrentInvocationsPerInstance metric. Historical analysis that runs for several hours is an appropriate use case for an Amazon SageMaker Processing job scheduled by Amazon EventBridge, providing a batch processing pipeline for model evaluation and refinement.
Question 11
An ML engineer has trained a neural network by using stochastic gradient descent (SGD). The neural network performs poorly on the test set. The values for training loss and validation loss remain high and show an oscillating pattern. The values decrease for a few epochs and then increase for a few epochs before repeating the same cycle.
What should the ML engineer do to improve the training process?
A. Introduce early stopping.
B. Increase the size of the test set.
C. Increase the learning rate.
D. Decrease the learning rate.
Show Answer
Correct Answer: D
Explanation: Decrease the learning rate. A rate that is too high can make SGD overshoot good parameter values, producing oscillating losses and preventing convergence. Smaller updates can stabilize training. Early stopping addresses overfitting, and changing test-set size does not improve optimization.
$19
Get all 237 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.