- A
Deploy the model on Cloud Run with minimum instances set to 1.
Why wrong: Cloud Run may still have cold start latency, and it is less optimized for model serving than TensorFlow Serving.
- B
Deploy the model as a Cloud Function triggered by HTTP requests.
Why wrong: Cloud Functions has cold starts and is not designed for real-time low-latency serving.
- C
Deploy the model on Vertex AI Prediction with a custom container.
Why wrong: Vertex AI Prediction adds managed infrastructure overhead, which can increase latency compared to a direct GKE deployment.
- D
Deploy TensorFlow Serving on GKE with a LoadBalancer service.
TensorFlow Serving is optimized for low-latency serving and can be configured on GKE with a LoadBalancer for direct access, minimizing network hops.
Quick Answer
The correct answer is to deploy TensorFlow Serving on GKE with a LoadBalancer service, as this configuration provides the lowest-latency path for real-time inference. TensorFlow Serving is purpose-built for high-performance model serving, supporting advanced batching and gRPC protocols that minimize overhead, while GKE offers fine-grained control over node placement, autoscaling, and networking to consistently meet the 100ms SLA. On the Google Professional Machine Learning Engineer exam, this question tests your understanding of optimizing inference latency by choosing the right infrastructure layer—specifically, that managed serverless options like Cloud Run or Vertex AI add cold-start latency and lack the low-level optimization for TensorFlow models, making them unsuitable for sub-100ms requirements. A common trap is assuming Vertex AI’s convenience always wins, but for ultra-low latency, direct GKE deployment with a LoadBalancer bypasses extra hops. Memory tip: “Direct GKE for low-latency, serverless for simplicity.”
PMLE Serving and scaling models Practice Question
This PMLE practice question tests your understanding of serving and scaling models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company is deploying a machine learning model for real-time fraud detection. The model must respond to requests within 100ms. The model is a TensorFlow model and will be deployed on Google Kubernetes Engine (GKE). Which Google Cloud service should be used to serve the model to minimize latency?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue:
"minimum / minimize"Why it matters: Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
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 TensorFlow Serving on GKE with a LoadBalancer service.
Option D is correct because deploying TensorFlow Serving directly on GKE with a LoadBalancer service provides the lowest-latency path for real-time inference. TensorFlow Serving is optimized for high-performance model serving with batching and gRPC support, and GKE allows fine-grained control over node placement, autoscaling, and networking to meet the 100ms SLA. In contrast, serverless options like Cloud Run or Cloud Functions add cold-start latency and lack the low-level optimization for TensorFlow models.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
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 the model on Cloud Run with minimum instances set to 1.
Why it's wrong here
Cloud Run may still have cold start latency, and it is less optimized for model serving than TensorFlow Serving.
- ✗
Deploy the model as a Cloud Function triggered by HTTP requests.
Why it's wrong here
Cloud Functions has cold starts and is not designed for real-time low-latency serving.
- ✗
Deploy the model on Vertex AI Prediction with a custom container.
Why it's wrong here
Vertex AI Prediction adds managed infrastructure overhead, which can increase latency compared to a direct GKE deployment.
- ✓
Deploy TensorFlow Serving on GKE with a LoadBalancer service.
Why this is correct
TensorFlow Serving is optimized for low-latency serving and can be configured on GKE with a LoadBalancer for direct access, minimizing network hops.
Clue confirmation
The clue word "minimum / minimize" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often assume Vertex AI Prediction is always the best choice for serving models, but for ultra-low-latency requirements (<100ms), a direct deployment on GKE with TensorFlow Serving avoids the overhead of a managed prediction platform.
Detailed technical explanation
How to think about this question
TensorFlow Serving uses gRPC (HTTP/2) for low-latency communication and supports model versioning, warm-up requests, and adaptive batching to maximize throughput under latency constraints. On GKE, you can pin pods to specific machine types (e.g., n2-highmem with GPUs) and use a LoadBalancer service with TCP proxy or internal load balancing to reduce network hops. In a real-world scenario, a fintech company processing credit card transactions would need to ensure the serving pod is co-located with the client application in the same VPC to avoid cross-region latency.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Serving and scaling models — study guide chapter
Learn the concepts, then practise the questions
- →
Serving and scaling models practice questions
Targeted practice on this topic area only
- →
All PMLE questions
506 questions across all exam domains
- →
Google Professional Machine Learning Engineer study guide
Full concept coverage aligned to exam objectives
- →
PMLE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related PMLE practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Scaling prototypes into ML models practice questions
Practise PMLE questions linked to Scaling prototypes into ML models.
Automating and orchestrating ML pipelines practice questions
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Collaborating within and across teams to manage data and models practice questions
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Architecting low-code ML solutions practice questions
Practise PMLE questions linked to Architecting low-code ML solutions.
Collaborating to manage data and models practice questions
Practise PMLE questions linked to Collaborating to manage data and models.
Serving and scaling models practice questions
Practise PMLE questions linked to Serving and scaling models.
Monitoring ML solutions practice questions
Practise PMLE questions linked to Monitoring ML solutions.
Solving business challenges with ML practice questions
Practise PMLE questions linked to Solving business challenges with ML.
PMLE fundamentals practice questions
Practise PMLE questions linked to PMLE fundamentals.
PMLE scenario practice questions
Practise PMLE questions linked to PMLE scenario.
PMLE troubleshooting practice questions
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Start a free PMLE practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this PMLE question test?
Serving and scaling models — This question tests Serving and scaling models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Deploy TensorFlow Serving on GKE with a LoadBalancer service. — Option D is correct because deploying TensorFlow Serving directly on GKE with a LoadBalancer service provides the lowest-latency path for real-time inference. TensorFlow Serving is optimized for high-performance model serving with batching and gRPC support, and GKE allows fine-grained control over node placement, autoscaling, and networking to meet the 100ms SLA. In contrast, serverless options like Cloud Run or Cloud Functions add cold-start latency and lack the low-level optimization for TensorFlow models.
What should I do if I get this PMLE question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "minimum / minimize". Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
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 →
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.