PMLE Practice Test 3 — 30 Questions

Question 1

A data analyst wants to build a binary classification model to predict customer churn using SQL queries in BigQuery. Which BigQuery ML model type should they use?

Accepted Answer

LOGISTIC_REG. BigQuery ML supports LOGISTIC_REG for binary classification via SQL. LINEAR_REG is for regression, K_MEANS for clustering, and MATRIX_FACTORIZATION for recommendations.

Answer

MATRIX_FACTORIZATION

Answer

LINEAR_REG

Answer

K_MEANS

Question 2

A retail company deploys a new recommendation model alongside the current champion on Vertex AI Endpoints. They want to gradually shift traffic to the challenger while monitoring business metrics (conversion rate). Which two steps are required? (Choose 2)

Accepted Answer

Deploy the challenger model to the same endpoint as the champion with a separate deployed model.. Vertex AI Endpoints support deploying multiple model versions (champion and challenger) to the same endpoint, each as a separate deployed model. This allows the endpoint to serve both models simultaneously, enabling traffic splitting without requiring separate endpoints or infrastructure.

Answer

Use Vertex AI Experiments to track the traffic split percentages.

Answer

Enable Cloud Memorystore to cache identical requests for both models.

Answer

Use Cloud Monitoring to track custom metrics like conversion rate per model version.

Question 3

A data scientist deployed a classification model on Vertex AI Endpoints. After a week, the model's accuracy drops significantly from 92% to 78%. The data scientist suspects training-serving skew. What is the first step to confirm this?

Accepted Answer

Compare feature distributions between training and serving data using Vertex AI Model Monitoring. Vertex AI Model Monitoring provides a built-in capability to automatically detect training-serving skew by comparing feature distributions between the training data and the live serving data. This is the most direct and efficient first step to confirm whether the accuracy drop is due to a shift in the input data distribution, which is the hallmark of training-serving skew. The data scientist can set up monitoring jobs that compute statistical distance metrics (e.g., Jensen-Shannon divergence) and alert when significant deviations occur.

Answer

Look for data leakage in the training pipeline

Answer

Examine the feature importance of the model

Answer

Check the prediction confidence over time

Question 4

You are monitoring a machine learning pipeline that runs on Vertex AI Pipelines. The pipeline occasionally fails with a 'ResourceExhausted' error when attempting to read data from BigQuery. Which action should you take to resolve this issue?

Accepted Answer

Reduce the complexity of the BigQuery query or increase the reservation size. The 'ResourceExhausted' error when reading from BigQuery indicates that the query is consuming more resources than the BigQuery reservation allows. Option C is correct because reducing query complexity (e.g., using fewer JOINs, aggregations, or partitions) or increasing the reservation size directly addresses the root cause by either lowering resource demand or allocating more capacity. Other options like switching to Cloud Storage or adjusting pipeline memory do not fix the BigQuery-specific quota or slot exhaustion.

Answer

Switch from BigQuery to Cloud Storage for data source

Answer

Increase the memory allocated to the pipeline step

Answer

Reduce the batch size of the data being read

Question 5

A data science team collaborates using Vertex AI Workbench user-managed notebooks. They want to version control their notebook code and share it with team members. Which TWO tools should they use? (Choose 2)

Accepted Answer

Git integration in Vertex AI Workbench. Git integration in Workbench allows version control, and sharing via Cloud Source Repositories or GitHub provides collaboration.

Answer

Cloud Functions

Answer

Vertex AI Model Registry

Answer

Vertex AI Experiments

Question 6

A company needs to serve a model for low-frequency inference requests (a few hundred per month) from multiple regions. The priority is simplicity and minimal cost without maintaining infrastructure. Which serving option should they choose?

Accepted Answer

Use Vertex AI Batch Prediction triggered as needed.. Vertex AI Batch Prediction runs on-demand jobs without any idle infrastructure cost, making it ideal for low-frequency inference requests (a few hundred per month) from multiple regions. Option A is wrong because a real-time endpoint with min replicas=1 incurs per-hour cost even when idle. Option B is wrong because Dataflow streaming pipelines are designed for continuous, real-time data processing, which adds complexity and cost for infrequent requests. Option D is wrong because Cloud Run scales to zero but is still a real-time serving option designed for online inference, not batch; it also requires containerized application and is not optimized for batch workloads.

Answer

Deploy a real-time Vertex AI Endpoint with min replicas set to 1.

Answer

Set up a Dataflow streaming pipeline to process requests.

Answer

Use Cloud Run with serving container and scale to zero.

Question 7

An ML engineer is building a monitoring dashboard for a Vertex AI pipeline that includes training, evaluation, and batch prediction. Which THREE components should be included to provide comprehensive observability? (Select THREE.)

Accepted Answer

Pipeline execution status, duration, and failure rates for each component.. Pipeline execution status, duration, and failure rates are fundamental metrics for monitoring the health and performance of a Vertex AI pipeline. These metrics allow the ML engineer to quickly identify bottlenecks, track overall workflow progress, and detect failures in training, evaluation, or batch prediction steps, which is essential for comprehensive observability.

Answer

Compute engine CPU and memory logs for each pipeline step.

Answer

Online prediction latency and request count from the deployed model endpoint.

Question 8

Refer to the exhibit. A user is trying to upload a Vertex AI pipeline definition. The error indicates an invalid dependency order. What should the user do to fix this?

Accepted Answer

Reorder the tasks in the YAML so that task1 is defined before task2.. Vertex AI pipeline definitions require that tasks be declared in the order they appear in the dependency graph. The YAML parser validates the `dependentTasks` field by checking that referenced tasks are already defined. Defining `task1` before `task2` ensures that when `task2` declares a dependency on `task1`, `task1` is already in scope, resolving the invalid dependency order error.

Answer

Rename task1 to a name that comes alphabetically before task2.

Answer

Change the dependency of task2 to be independent of task1.

Answer

Remove the dependentTasks field from task2 and rely on implicit ordering.

Question 9

You are designing an ML pipeline for a large-scale recommendation system that runs weekly retraining on historical user interaction data. The pipeline uses TensorFlow and is deployed on Google Cloud. The pipeline must be orchestrated and automated with minimal manual intervention. Which THREE options should you include in your design? (Choose three.)

Accepted Answer

Use Vertex AI Pipelines to define the ML pipeline as a Directed Acyclic Graph (DAG) of components.. Vertex AI Pipelines (option B) is correct because it provides a managed, serverless orchestration service for building, testing, and deploying ML pipelines as Directed Acyclic Graphs (DAGs). This directly supports the requirement for automated, minimal-intervention weekly retraining by allowing you to define reusable components and schedule pipeline runs via Cloud Scheduler or event triggers, integrating natively with TensorFlow and Google Cloud services.

Answer

Use BigQuery scheduled queries to run the training script on a schedule.

Answer

Use AI Platform Notebooks to schedule the training job on a recurring basis.

Question 10

You have a very large language model that does not fit on a single GPU. You need to train it efficiently across multiple GPUs on a single machine. Which approach should you use?

Accepted Answer

Model parallelism using pipeline parallelism. When a model is too large for a single GPU, model parallelism (specifically pipeline parallelism) splits the model across GPUs. Data parallelism would require each GPU to hold the full model, which is not possible.

Answer

Data parallelism with MirroredStrategy

Answer

Data parallelism with MultiWorkerMirroredStrategy

Answer

Use TPU training as TPUs have more memory

Question 11

A team wants to ensure that only approved models are deployed to production. Which Vertex AI feature should they use?

Accepted Answer

Vertex AI Model Registry with versioning and alias.. Vertex AI Model Registry with versioning and alias (Option E) is the correct feature because it allows teams to manage model lifecycle, track approved versions, and assign aliases (e.g., 'champion' or 'production') to designate which model is approved for deployment. This ensures only vetted models are promoted to production, aligning with governance and compliance requirements.

Answer

Vertex AI Experiments.

Answer

Cloud DLP.

Answer

Vertex AI Pipelines.

Answer

Vertex AI Feature Store.

Question 12

An ML engineer is deploying a large BERT-based natural language processing model for real-time inference on Vertex AI Prediction. The model has a large memory footprint (2GB) and experiences unpredictable traffic spikes up to 10x the baseline. The engineer needs to minimize latency and cost while handling spiky traffic. Which TWO actions should the engineer take? (Choose two.)

Accepted Answer

Use a custom prediction routine with model quantization to reduce model size.. Model quantization reduces the memory footprint of a BERT model (e.g., from 2GB to ~500MB with INT8 quantization), which directly lowers inference latency and cost by enabling faster loading and more efficient use of hardware. This is critical for real-time inference with unpredictable traffic spikes, as smaller models scale more easily and reduce the need for excessive replicas.

Answer

Configure the endpoint to use manual scaling with a fixed number of replicas equal to peak traffic.

Answer

Enable automatic scaling with a maximum of 3 replicas to limit cost.

Answer

Set up model monitoring to detect prediction drift and retrain regularly.

Question 13

A data scientist trains an XGBoost model on Vertex AI with a custom container. The model performs well on a held-out test set but fails to generalize in production. They suspect data leakage between training and validation. What is the best practice to prevent this?

Accepted Answer

Store and serve features using Vertex AI Feature Store with point-in-time correctness. Vertex AI Feature Store with point-in-time correctness ensures that for each training example, only feature values that were known at the time of the prediction (i.e., before the label occurred) are used. This prevents future data from leaking into the training set, which is the most common cause of poor generalization when temporal ordering matters. The Feature Store automatically retrieves the latest feature value as of a specified timestamp, eliminating the need for manual joins and windowing logic.

Answer

Implement feature engineering in Vertex AI Pipelines to ensure temporal ordering

Answer

Store all features in BigQuery and join on timestamp during training and serving

Answer

Use Vertex AI AutoML instead of custom training

Question 14

What is the primary purpose of Vertex AI Edge Manager?

Accepted Answer

To deploy and manage ML models on edge devices at scale. Vertex AI Edge Manager is specifically designed to deploy, monitor, and manage ML models on edge devices at scale. It handles model packaging, over-the-air updates, and health monitoring across fleets of edge devices, which is distinct from simply running batch predictions or converting model formats.

Answer

To run batch predictions on edge devices

Answer

To convert models to TensorFlow Lite automatically

Answer

To train models on edge devices using federated learning

Question 15

A team wants to implement automated model documentation that captures training data, feature importance, evaluation metrics, and intended use. Which Vertex AI feature supports this?

Accepted Answer

Vertex AI Model Registry with model cards. Model cards in Vertex AI Model Registry provide a standardised template for documenting model details.

Answer

Vertex AI Metadata

Answer

Vertex AI Explainable AI

Answer

Vertex AI Pipelines

Question 16

You need to preprocess a large dataset (terabytes) for training a TensorFlow model. The preprocessing includes scaling and bucketizing features, and the same transformations must be applied during serving. Which tool should you use?

Accepted Answer

Dataflow with Apache Beam and tf.Transform. TensorFlow Transform (tf.Transform) allows you to define preprocessing pipelines that are applied consistently during training and serving. It computes statistics over the full dataset and creates a TensorFlow graph for serving.

Answer

Dataproc with Spark ML

Answer

Vertex AI Feature Store

Answer

BigQuery ML

Question 17

A company trains models using Vertex AI Training and wants to share the resulting model artifacts with a different team in another Google Cloud project. What is the most secure way to grant access?

Accepted Answer

Create a new service account in the other project, then grant it the 'roles/storage.objectViewer' role on the bucket.. It follows the principle of least privilege and cross-project access best practices. By creating a dedicated service account in the target project and granting it the 'roles/storage.objectViewer' role on the specific Cloud Storage bucket, you avoid exposing the bucket publicly and avoid sharing the Vertex AI model resource directly, which would grant broader permissions than necessary. This approach ensures that only the service account can read the model artifacts, and the other team can use that service account to access the bucket securely.

Answer

Use BigQuery to copy the model artifacts and share the BigQuery dataset.

Answer

Share the Vertex AI model resource directly by adding the other project's members to the IAM policy on the model.

Answer

Set the Cloud Storage bucket containing the artifacts to 'public' access.

Question 18

Refer to the exhibit. An ML engineer in the team needs to deploy the model to an endpoint. The engineer is assigned the 'roles/aiplatform.user' role at the project level but still cannot deploy. What is the most likely reason?

Accepted Answer

The model's resource-level IAM policy only grants the 'roles/aiplatform.user' role, which does not include deploy permission.. The 'roles/aiplatform.user' role at the project level grants permissions to use AI Platform resources, but it does not include the 'aiplatform.models.deploy' permission required to deploy a model to an endpoint. Model deployment is controlled by resource-level IAM policies, and if the model's resource-level policy only grants 'roles/aiplatform.user', the deploy action is denied. The correct role for deployment is 'roles/aiplatform.admin' or a custom role with the deploy permission.

Answer

The service account 'sa-training' is using all the model's quota.

Answer

Alice does not have any IAM role on the project.

Answer

Alice needs to be granted the 'roles/aiplatform.admin' role at the project level.

Question 19

To enable collaboration on notebook-based experiments across teams, what is the recommended approach in Google Cloud?

Accepted Answer

Use Colab Enterprise notebooks with shared runtimes and IAM permissions. Colab Enterprise notebooks with shared runtimes and IAM permissions is the recommended approach because it provides a fully managed, collaborative environment where multiple users can work on the same notebook simultaneously, with fine-grained access control via IAM and consistent runtime configurations. This eliminates version conflicts and environment drift, which are common in distributed notebook workflows.

Answer

Share Docker images containing the notebook environment

Answer

Each team member works on their own local Jupyter notebook and shares screenshots

Answer

Store notebooks in a Cloud Storage bucket and open them with Vertex AI Workbench

Question 20

A data scientist trained a model on a single GPU but needs to train on multiple GPUs for a larger dataset. They observe that training time does not decrease linearly with additional GPUs. Which common issue is most likely?

Accepted Answer

Data pipeline bottleneck.. Data pipeline bottleneck. When training on multiple GPUs, the expected speedup is linear if data loading and preprocessing can keep up with the GPUs. However, if the data pipeline is slow (e.g., due to disk I/O, network latency, or insufficient CPU preprocessing), GPUs will spend time idle waiting for data, preventing linear scaling. Option A is incorrect because overfitting affects model accuracy, not training speed. Option B is incorrect because model architecture simplicity does not directly cause non-linear speedup; simpler architectures may actually speed up training. Option C is incorrect because learning rate affects convergence behavior, not the efficiency of parallel training.

Answer

Overfitting.

Answer

Model architecture too simple.

Answer

Learning rate too high.