A fintech company serves a fraud-detection model that needs real-time features like transaction velocity. The features are computed in a streaming pipeline and stored in Vertex AI Feature Store. The model is deployed to a Vertex AI endpoint. How should the serving application retrieve features for each prediction request?

Call the Feature Store online serving endpoint with the entity ID to fetch features, then pass them to the model endpoint

Query BigQuery directly for the features at prediction time

Embed the features in the model's input payload and skip the Feature Store

Use the Feature Store batch serving endpoint to precompute features for all users

Google CloudProfessional Machine Learning Engineer

Domain 4Objective 2

Scaling Online Model Serving PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 8)

Part of the Serving and scaling models domain, which accounts for ~20% of the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam.

37questions here

8free pages

14concepts

~20%of the exam

14 Concepts in This Objective

Feature Store fundamentals
Serving features from Feature Store
Feature Store configuration and monitoring
Public and private endpoints
Deploying models to endpoints
Endpoint security and access control
Hardware selection for serving
Hardware optimization and cost trade-offs
Scaling serving infrastructure
Containerized serving and inference platforms
Throughput and latency management
Model tuning for production
Serving-specific model optimization
Production model lifecycle management

Questions 36–37

36foundation · easy
Which hardware is typically best suited for serving a large transformer-based language model with low latency?
Select an answer first
37application · medium
A fintech company serves a fraud-detection model that needs real-time features like transaction velocity. The features are computed in a streaming pipeline and stored in Vertex AI Feature Store. The model is deployed to a Vertex AI endpoint. How should the serving application retrieve features for each prediction request?
Select an answer first

Finished these 2 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to PROFESSIONAL-MACHINE-LEARNING-ENGINEER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Google Cloud. “PROFESSIONAL-MACHINE-LEARNING-ENGINEER” is a trademark of its owner, used for identification only.

Scaling Online Model Serving PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice Questions (Page 8)

Questions 36–37

Which hardware is typically best suited for serving a large transformer-based language model with low latency?

Keep studying — Serving and scaling models