PMLE Serving and Scaling Models Practice Question
A retail team must run nightly batch predictions over 20 TB of Parquet data stored in Cloud Storage using a custom PyTorch model registered in Vertex AI Model Registry. They want the job to finish within a fixed maintenance window and prefer not to manage the underlying compute. Which configuration should they use?
⚠ Common exam trap
The trap here is assuming that a CustomJob or an online endpoint is needed for large-scale inference when the managed batch prediction service already covers it.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Create a Vertex AI BatchPredictionJob with the model from Model Registry, set the input to the Cloud Storage Parquet path, and specify a machine type plus a starting and maximum replica count for the distributed workers.
Batch prediction is purpose-built for large offline scoring: it reads files directly from Cloud Storage, distributes work across managed replicas, and writes sharded output without any endpoint. Specifying machine type and replica bounds gives the team control over throughput so the job completes inside the maintenance window while Vertex AI handles provisioning.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Schedule the model on a Vertex AI pipeline with a Dataflow step that calls the endpoint for each record, using streaming inserts to write results back to Cloud Storage.
Why it's wrong here
Routing every record through an online endpoint reintroduces per-request latency and quota pressure, and streaming inserts are a BigQuery pattern rather than a Cloud Storage write mechanism. The pipeline adds orchestration complexity while leaving the core inference path inefficient for a large nightly batch.
- ✗
Deploy the model to a Vertex AI endpoint with autoscaling and write a client script that submits all rows as individual online prediction requests.
Why it's wrong here
Online prediction is designed for low-latency, low-volume traffic; sending billions of rows as individual requests incurs per-request overhead, endpoint quota limits, and sustained cost. It also requires managing a long-running client, and the endpoint would need to stay scaled up for hours, which is impractical for a nightly 20 TB job.
- ✗
Create a Vertex AI CustomJob that runs a PyTorch training script with the input path as a parameter, since CustomJob automatically performs batch inference when given a Parquet input.
Why it's wrong here
A CustomJob executes whatever container command you provide; it has no built-in notion of batch inference, output sharding, or prediction result writing. Using it here means writing all inference and output logic yourself, which contradicts the goal of a managed batch prediction configuration.
- ✓
Create a Vertex AI BatchPredictionJob with the model from Model Registry, set the input to the Cloud Storage Parquet path, and specify a machine type plus a starting and maximum replica count for the distributed workers.
Why this is correct
Batch prediction reads directly from Cloud Storage, shards the input across workers, and scales horizontally according to the replica count you configure, all on managed infrastructure. Setting a maximum replica count lets the job finish within the maintenance window without the team provisioning or patching any compute themselves.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.