Home › GCP ML Engineer › cloudcomputing › mleops › Which GCP service should an ML Engineer use to D…
Which GCP service should an ML Engineer use to DEPLOY a fine-tuned LLM as a serverless container endpoint — with traffic-based autoscaling and per-request billing?
ACloud DNS
BCloud Run (with a model-serving container) — or a Vertex AI endpoint for full ML platform integration
CCloud Memorystore
DLong-lived VM with manual scaling
Answer & Solution
Correct answer: B. Cloud Run (with a model-serving container) — or a Vertex AI endpoint for full ML platform integration
Cloud Run is GCP's serverless-container runtime (per PMLE §5.1). The other options aren't serverless.
Related questions
Which GCP service should an ML Engineer use to schedule recurring ML pipeline runs (e.g. rWhich Vertex AI capability should an ML Engineer use to evaluate a GENERATIVE-AI solution Which CI/CD pattern should an ML Engineer adopt for automated MODEL RETRAINING when new daWhich Responsible AI consideration should an ML Engineer evaluate BEFORE deploying a hirinWhich Vertex AI Model Monitoring signal should an ML Engineer track to detect when INPUT FWhich Vertex AI capability should an ML Engineer use to PRODUCE feature-level explanationsWhich Vertex AI service should an ML Engineer use to MONITOR a deployed model for drift beWhich Vertex AI service should an ML Engineer use to TRACK lineage of ML artifacts across