Which service should you use to deploy real-time inference behind an endpoint?
Multiple choice — select one answer
Answer choices
Architectural breakdown & explanation
Endpoints serve low-latency predictions.
Correct answer(s): a. SageMaker real-time endpoints
Exam domain: Domain 3: Deployment and Orchestration of ML Workflows (24% weight on the official guide).
Official documentation & study links
Practice this certification
This page is one question from the AWS Certified Machine Learning Engineer – Associate bank. Run a full timed practice exam with domain-weighted random questions in your browser.