Parks already serves three internal APIs on Amazon ECS. They want the trail-washout severity model packaged as one more service on that cluster, with the same deploy path, not a new SageMaker endpoint estate. Which target fits?
Select an answer to reveal the explanation.
Short Explanation
Parks already serves three APIs on ECS. Package the trail-washout model as one more service on that cluster. A new SageMaker estate is extra, Fraud Detector is not ECS, and Lambda is the wrong jump for a long-running service.
Full Explanation
Amazon ECS is the deployment target when inference already runs as a long-running service on that cluster. This is target selection, not a new SageMaker estate. Fraud Detector is not ECS, and Lambda is the wrong jump for a long-running service.