Question

A retail company runs a real-time SageMaker endpoint that serves product recommendations during business hours. The endpoint is currently configured with a single ml.c5.xlarge instance in one production variant. During a recent Availability Zone disruption, the endpoint became completely unavailable, causing a customer-facing outage. The ML engineering team must improve availability with minimal configuration changes and without over-provisioning. What is the most effective change to make?

Accepted Answer

Increase the production variant's initial instance count to at least 2 so SageMaker distributes instances across multiple Availability Zones.

Answer

Switch the endpoint to a serverless inference configuration to eliminate the need for Availability Zone management.

Answer

Deploy a second identical endpoint in a different AWS Region and configure Route 53 failover routing.

Answer

Enable data capture on the endpoint so failed requests are logged and can be replayed after recovery.