Select deployment infrastructure based on existing architecture and requirements.
10 practice questions under this official exam objective (MLA-C01), each with the answer key, an option-by-option explanation and instant feedback.
Questions under this objective
10 total · page 1 of 1Using the SageMaker Model Registry and Model Groups to Version ML Models with Least Overhe
A company building a web-based AI application on SageMaker needs experimentation, training, a central model registry, deployment, and monitoring, and
Grouping SageMaker Model Groups into Collections Without Modifying Underlying Model Artifa
Hundreds of data scientists work in three categories, computer vision, NLP, and speech recognition, and the existing models in SageMaker Model Registr
How to Make SageMaker Endpoint Auto Scaling Most Responsive?
For a SageMaker real-time endpoint that must react quickly to traffic spikes, this page explains why high-resolution InvocationsPerInstance metrics an
How to Deploy a Nightly SageMaker Prediction Model?
A once-nightly, sub-minute prediction with a 3 MB payload is best served by SageMaker Serverless Inference because it scales to zero between runs and
Building a Cross-Account Central Model Catalog with SageMaker Model Registry and Model Gro
A company needs a central catalog for all of its ML models, which live in the AWS accounts where they were originally developed and are hosted in ECR
Copying a Comprehend Custom Model Between AWS Accounts with ImportModel and a Resource-Bas
An ML engineer has an Amazon Comprehend custom model in Account A in us-east-1 and needs to copy it into Account B in the same region with the least d
Real-Time Clickstream Pipeline with Amazon MSK and Managed Flink for SQL Processing and Vi
A company needs a real-time pipeline for high-volume ecommerce clickstream data that must be ingested, processed, and visualized in near real time, an
SageMaker Traffic Shifting Strategies for ML Model Deployment
This question tests the selection of appropriate Amazon SageMaker traffic shifting strategies based on specific deployment risk and rollback requireme
How Should SageMaker AI Serve High-Resolution Image Cost Predictions with User Notificatio
This scenario tests how to pick the right SageMaker AI inference pattern and notification service for large image payloads that take time to process.
Amazon SageMaker AI Model Deployment Strategies
This page explains how to select the correct Amazon SageMaker AI deployment strategy (Canary, Linear, or All at once) based on specific business requi