Practice free →
HomeGCP ML Engineercloudcomputingmleserving › Which Vertex AI capability should an ML Engineer…

Which Vertex AI capability should an ML Engineer use to serve a trained model as a low-latency HTTPS endpoint — autoscaling on request volume?

ACloud Memorystore
BCloud DNS
CManually deploying a Flask app on a single VM
DVertex AI Prediction online endpoint
Answer & Solution
Correct answer: D. Vertex AI Prediction online endpoint
Vertex AI Prediction online endpoint is the canonical autoscaling serving (per PMLE §4.1). The others don't autoscale.
Solve this in the app — GCP ML Engineer practice & 24k+ MCQs →
Related questions