Question 769 of 990
mediumMultiple ChoiceObjective-mapped
Scaling a TensorFlow Model to Production
A machine learning team has a prototype using a custom TensorFlow model trained on a small dataset stored in Cloud Storage. They want to scale the prototype to production with minimal code changes while ensuring the model can handle increased traffic and new data. The model currently loads data using tf.data.Dataset from CSV files. Which approach best meets these requirements?
Quick Answer
The answer is to use Vertex AI Training with hyperparameter tuning and distributed training, then deploy the model to Vertex AI Prediction with autoscaling. This approach is correct because it leverages Vertex AI’s managed infrastructure to scale the existing tf.data pipeline for larger datasets and increased traffic without requiring any changes to the custom TensorFlow model code. On the Google Professional Machine Learning Engineer exam, this scenario tests your understanding of how to transition from prototype to production using fully managed services while preserving the original model architecture. A common trap is assuming you must rewrite the model for TensorFlow Serving or convert it to a different format, but Vertex AI Prediction natively supports custom TensorFlow models and autoscaling. Remember the key principle: keep the code, change the infrastructure. Memory tip: “Train with tuning, serve with scaling—no code rewriting.”
⚠ Common exam trap
The trap here is that candidates may overcomplicate by choosing containerization (B) or a completely different platform (C), missing that Vertex AI Prediction natively supports TensorFlow models with autoscaling and minimal code changes.
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
✓
Use Vertex AI Training with hyperparameter tuning and distributed training, then deploy the model to Vertex AI Prediction with autoscaling.
Vertex AI Prediction with autoscaling directly addresses the need to handle increased traffic without code changes, while Vertex AI Training with hyperparameter tuning and distributed training enables scaling to larger datasets with minimal modifications to the existing tf.data pipeline. This approach keeps the custom TensorFlow model intact and leverages managed infrastructure for both training and serving.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Use Vertex AI Training with hyperparameter tuning and distributed training, then deploy the model to Vertex AI Prediction with autoscaling.
Why this is correct
Vertex AI provides seamless scaling with minimal code changes and supports tf.data.Dataset.
- ✗
Deploy the model to AI Platform (Unified) Prediction with a custom container, and use AI Platform Training to retrain on larger datasets.
Why it's wrong here
AI Platform (Unified) is deprecated; Vertex AI is the recommended service.
- ✗
Migrate the model to BigQuery ML and use SQL for training and prediction to leverage BigQuery's scalability.
Why it's wrong here
BigQuery ML requires rewriting the model and does not support custom TensorFlow models directly.
- ✗
Package the model as a Cloud Run Function and use Cloud Scheduler to trigger retraining periodically.
Why it's wrong here
Cloud Run Functions are stateless and have request limits, not suitable for ML serving.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on PMLE
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A team has a trained TensorFlow model running locally and wants to deploy it for low-latency online predictions on Google Cloud. Which service should they use?
easy- ✓ A.Vertex AI Prediction
- B.AI Platform Training
- C.Cloud Run
- D.Cloud Functions
Why A: Vertex AI Prediction is the correct choice because it is a fully managed service designed specifically for deploying trained ML models for online (real-time) prediction with low latency. It supports importing TensorFlow SavedModel artifacts and automatically scales the serving infrastructure, including GPU/TPU support, to handle request traffic while providing built-in monitoring and explainability features.
Last reviewed: Jun 11, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.