Home › GCP ML Engineer › cloudcomputing › mleserving › Which GCP service should an ML Engineer use to s…
Which GCP service should an ML Engineer use to serve a model directly inside BigQuery as a SQL function — for analyst-driven batch scoring with no separate endpoint?
ABigQuery ML's ML.PREDICT (or a remote model pointing to a Vertex AI endpoint)
BCloud Memorystore
CCloud DNS
DManually exporting BQ data to CSV + scoring on a laptop
Answer & Solution
Correct answer: A. BigQuery ML's ML.PREDICT (or a remote model pointing to a Vertex AI endpoint)
BigQuery ML ML.PREDICT scores within BQ (per PMLE §4.1). The other options aren't in-DB scoring.
Related questions
Which Vertex AI capability should an ML Engineer use to serve XGBoost / LightGBM / scikit-Which GCP-compatible streaming runtime should an ML Engineer use to MAKE PREDICTIONS over Which Vertex AI feature should an ML Engineer use to deploy a CUSTOM container that wraps Which Vertex AI deployment option should an ML Engineer choose for a HIGH-THROUGHPUT onlinWhich ML model-optimisation technique should an ML Engineer use to REDUCE inference latencWhich Vertex AI Feature Store capability should an ML Engineer use to FETCH a feature vectWhich Vertex AI endpoint type should an ML Engineer recommend to keep model traffic INSIDEWhich Vertex AI feature should an ML Engineer use to run an A/B test between two model ver