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

Which Vertex AI capability should an ML Engineer use to run a HIGH-VOLUME inference job over a finished dataset — not real-time — referenced in PMLE §4.1?

ACloud DNS
BCloud Memorystore
COnline endpoint scaled to one instance
DVertex AI batch prediction
Answer & Solution
Correct answer: D. Vertex AI batch prediction
Vertex AI batch prediction is the offline-inference path (per PMLE §4.1). Online endpoints are for low-latency requests; the others aren't inference.
Solve this in the app — GCP ML Engineer practice & 24k+ MCQs →
Related questions