mediumMultiple Choice
PMLE Practice Question: A data scientist trained a custom TensorFlow…
A data scientist trained a custom TensorFlow model using Vertex AI Training and wants to deploy it for online predictions with low latency (<100ms). Which deployment option on Google Cloud is best?
⚠ Common exam trap
Google Cloud often tests the misconception that any serverless option (like Cloud Run or Cloud Functions) is sufficient for low-latency ML inference, ignoring the need for GPU acceleration and optimized serving infrastructure that only Vertex AI Endpoints provides.
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
✓
Deploy on Vertex AI Endpoints
Vertex AI Endpoints is the correct choice because it is purpose-built for deploying TensorFlow models with optimized serving infrastructure, including automatic scaling, GPU/TPU support, and built-in monitoring for latency-sensitive online predictions. It provides a managed endpoint that can achieve sub-100ms latency by leveraging model optimization techniques like TensorFlow Serving and hardware accelerators, which are not available in the other options.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Deploy on Cloud Run with a custom container
Why it's wrong here
Cloud Run serves HTTP containers but lacks Vertex AI's model server, GPU-attached prediction nodes and autoscaling tuned for inference, so consistent sub-100ms latency is not assured. It is tempting because the model can be wrapped in a container cheaply. Vertex AI Endpoints is designed for this serving requirement.
- ✗
Deploy on Cloud Functions
Why it's wrong here
Cloud Functions caps execution at 60 minutes and cold starts add latency, so sub-100ms online serving of a TensorFlow model is unattainable; it suits event-driven, lightweight inference triggered by HTTP or Pub/Sub rather than sustained low-latency prediction traffic.
- ✗
Deploy on AI Platform Prediction (legacy)
Why it's wrong here
AI Platform Prediction (legacy) lacks the current Vertex AI online prediction serving stack and its optimised low-latency infrastructure, so sub-100ms targets are not reliably met. It is tempting for existing legacy pipelines already integrated with that endpoint. Vertex AI Endpoints with a suitable machine type is the intended choice.
- ✓
Deploy on Vertex AI Endpoints
Why this is correct
Vertex AI Endpoints serve models for online prediction with autoscaling and low-latency inference, meeting the sub-100ms requirement. Batch prediction cannot serve real-time requests, and deploying the TensorFlow model directly to Endpoints uses the managed serving stack rather than custom infrastructure.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.