Amazon Web Services SAP-C02 Exam With Confidence Using Practice Dumps

B is correct because SageMaker AI multi-model endpoints are designed for hosting a large number of models that use the same ML framework behind shared serving infrastructure. This is exactly the pattern for a SaaS platform with thousands of tenant-specific models. A dedicated endpoint per model would create excessive cost and management overhead. Serverless endpoints reduce instance management but do not solve the cost problem of managing thousands of separate model deployments. Asynchronous inference and batch transform are not appropriate because the requirement includes sub-200 ms latency, which requires real-time inference. AWS documentation states that multi-model endpoints are ideal for hosting many models using the same framework and can provide higher cost savings by sharing resources across models.

The best solution for this problem is to update the visibility timeout for the SQS queue to 3 hours. This is because when the visibility timeout is set to 1 hour, it means that if the EC2 instance doesn ' t process the message within an hour, it will be moved to the dead-letter queue. By increasing the visibility timeout to 3 hours, this should give the EC2 instance enough time to process the message before it gets moved to the dead-letter queue. Additionally, configuring scale-in protection for the EC2 instances during processing will help to ensure that the instances are not terminated while the messages are being processed.

The best solution is to create an RSA key pair that is dedicated to the data-handling microservice and upload the public key to the CloudFront distribution. Then, create a field-level encryption profile and a configuration, and add the configuration to the CloudFront cache behavior. This solution will ensure that the sensitive data is encrypted at the edge locations of CloudFront, close to the end users, and remains encrypted throughout the application stack. Only the data-handling microservice, which has access to the private key of the RSA key pair, can decrypt the data. This solution does not require any additional resources or code changes, and leverages the built-in feature of CloudFront field-level encryption. For more information about CloudFront field-level encryption, see Using field-levelencryption to help protect sensitive data.