PMLE Practice Exam 54 — 20 Questions

Question 1

Your team deploys a model using Vertex AI Endpoints with autoscaling. Which TWO metrics are most important to monitor in order to optimize cost and performance? (Choose two.)

Accepted Answer

Number of requests per minute.. The number of requests per minute directly drives autoscaling behavior in Vertex AI Endpoints. Monitoring this metric allows you to right-size the number of serving nodes to match traffic patterns, avoiding over-provisioning (cost) or under-provisioning (performance). Option C is correct because CPU utilization of the serving containers indicates whether the model is compute-bound or idle; high CPU suggests the need for more nodes, while low CPU suggests over-provisioning, directly impacting both cost and latency.

Answer

Number of active nodes in the endpoint.

Answer

Error rate (HTTP 4xx/5xx).

Answer

P99 prediction latency.

Question 2

A company wants to implement a central model governance strategy using Vertex AI. They need to track model lineage, store evaluation metrics, and manage model versions across teams. Which THREE Vertex AI services should they use? (Choose 3)

Accepted Answer

Vertex AI Metadata. Vertex AI Metadata tracks lineage, Model Registry stores models and versions with evaluation metrics, and Experiments captures run parameters and metrics.

Answer

Vertex AI Workbench

Answer

Vertex AI Feature Store

Question 3

An ML engineer needs to deploy a model from Vertex AI Model Registry to an endpoint. The model has multiple versions. They want to designate one version as the 'champion' for production traffic. How should they do this?

Accepted Answer

Use the 'champion' alias. Vertex AI Model Registry supports aliases; assigning the 'champion' alias to a model version allows routing production traffic to that version.

Answer

Set the version as default in the registry

Answer

Use the 'production' alias

Answer

Deploy the model directly to an endpoint without alias

Question 4

An ML team wants to share feature definitions across multiple projects to reduce training-serving skew and ensure consistency. They currently store features in Cloud Storage and manually coordinate updates, leading to errors. Which Google Cloud service should they use to centrally manage and serve features for both training and online inference?

Accepted Answer

Vertex AI Feature Store. Vertex AI Feature Store centralizes feature management, providing an online store for low-latency serving and an offline store for training data retrieval, reducing training-serving skew.

Answer

Cloud Data Catalog

Answer

Vertex AI Model Registry

Answer

Cloud Storage with versioning

Question 5

A data science team wants to share a set of engineered features across multiple projects and teams to reduce training-serving skew and ensure consistency. They need low-latency serving (single-digit milliseconds) for online predictions and also need to retrieve historical feature values for training. Which approach should they take?

Accepted Answer

Use Vertex AI Feature Store to define features once, serve online predictions from the online store, and retrieve historical features from the offline store for training.. Vertex AI Feature Store is designed exactly for this purpose: it centralizes feature definitions and serves features online (using an online store) and offline (using BigQuery). The online store provides low-latency serving, and point-in-time queries allow training data creation without data leakage. This reduces training-serving skew across teams.

Answer

Create a shared BigQuery dataset where each team writes features; serve predictions by querying BigQuery synchronously.

Answer

Store features in Cloud Storage Parquet files and load them into BigQuery for training; serve predictions from a custom microservice that reads from Cloud Storage.

Answer

Use Cloud Memorystore (Redis) to store the latest feature values for low-latency serving; each team independently computes features and pushes to Redis.

Question 6

Which Vertex AI service is used to track the lineage of ML pipeline components, artefacts, and executions?

Accepted Answer

Vertex AI Metadata. Vertex AI Metadata (ML Metadata) stores and queries lineage information.

Answer

Vertex AI Model Registry

Answer

Vertex AI Feature Store

Answer

Vertex AI Experiments

Question 7

A machine learning team wants to implement champion/challenger model deployment. They have two model versions: v1 (champion) and v2 (challenger). They deploy both to the same endpoint with traffic splitting. How should they manage model versions in Vertex AI Model Registry to reflect this?

Accepted Answer

Upload v1 with alias 'champion' and v2 with alias 'challenger'. Then deploy both to the endpoint with traffic split.. Aliases in Model Registry allow labeling models as 'champion' and 'challenger' for easy identification and traffic routing.

Answer

Upload both models without aliases. Use endpoint traffic splitting by model version ID.

Answer

Use Vertex AI Experiments to designate champion/challenger.

Answer

Create two separate endpoints: one for champion and one for challenger.

Question 8

A data science team wants to version control their datasets along with code using Git. They need a tool that integrates with Git and tracks changes to large data files. Which tool should they use?

Accepted Answer

DVC. DVC (Data Version Control) is designed to version large datasets and models alongside Git, storing data in remote storage and metadata in Git.

Answer

BigQuery table snapshots

Answer

Delta Lake

Answer

Git LFS

Question 9

A team uses Vertex AI Workbench notebooks for collaborative model development. They want to ensure that code changes are version-controlled, that multiple data scientists can work on the same notebook without conflicts, and that the environment is reproducible across team members. Which approach should they take?

Accepted Answer

Use Vertex AI Workbench managed notebooks with Git integration and a custom container image for environment reproducibility.. Vertex AI Workbench supports Git integration for version control. Using a user-managed notebook with a custom container image (Docker) ensures environment reproducibility. This allows multiple data scientists to clone the same repo, make changes in isolation, and merge code. The managed notebook option also supports Git, but user-managed provides flexibility for custom environments.

Answer

Use a shared JupyterLab instance launched on a single VM; data scientists connect simultaneously.

Answer

Store notebooks in Cloud Storage and share the bucket; each user edits their own copy.

Answer

Use Vertex AI Pipelines to run all code as pipelines; data scientists only view results in notebooks.

Question 10

A data analyst wants to build a binary classification model using a low-code ML solution on Google Cloud. The dataset is stored in BigQuery and contains 500,000 rows with 20 features, including categorical and numerical columns. The analyst has minimal coding experience and needs to deploy the model as an API endpoint for real-time predictions. Which two Google Cloud services should the analyst use to accomplish this task with minimal code? Choose two options.

Accepted Answer

Vertex AI Endpoints. Vertex AI Endpoints is correct because it provides a managed service to deploy trained models as REST API endpoints for real-time predictions with minimal code. The analyst can deploy an AutoML Tables model directly to a Vertex AI Endpoint, enabling low-code deployment and serving.

Answer

BigQuery ML

Answer

Cloud Functions

Answer

Vertex AI Workbench

Question 11

A team is building a fraud detection model that requires joining real-time transaction features with historical user features. They need to ensure that the training data does not use future information (data leakage). Which Vertex AI Feature Store capability should they use?

Accepted Answer

Point-in-time correct join. Point-in-time correct join ensures that at training time, each row is joined with the feature value as it existed at that specific point in time, preventing leakage from future feature values.

Answer

Online store serving with Bigtable

Answer

Feature store time travel

Answer

Feature monitoring for drift

Question 12

A company uses Vertex AI Pipelines to orchestrate ML workflows. After a pipeline run, they want to query the lineage of a particular model artifact to find out which dataset and hyperparameters were used to produce it. Which API method should they use?

Accepted Answer

projects.locations.metadataStores.artifacts.queryArtifactLineageSubgraph. Vertex AI Metadata allows querying lineage via the lineagesubgraph method to retrieve upstream and downstream artifacts.

Answer

projects.locations.metadataStores.artifacts.get

Answer

projects.locations.metadataStores.contexts.addContextArtifactsAndExecutions

Answer

projects.locations.metadataStores.executions.queryExecutionInputsAndOutputs

Question 13

A team is operationalizing a machine learning pipeline using Vertex AI. They want to automatically track experiment runs, log model parameters and metrics, and store model artifacts for reproducibility. They also need to capture lineage between pipeline components (e.g., which dataset and hyperparameter tuning job produced a model). Which TWO services should they use together to achieve this? (Choose two.)

Accepted Answer

Vertex AI Metadata. Vertex AI Experiments provides experiment tracking (parameters, metrics, artifacts). Vertex AI Metadata captures lineage between pipeline components, artifacts, and executions. Together, they enable full reproducibility and traceability.

Answer

Vertex AI Model Registry

Answer

Vertex AI Feature Store

Answer

Vertex AI Workbench

Question 14

A team uses Vertex AI Pipelines with CustomJob components that pull training code from a Cloud Source Repository. The pipeline fails with a 'Permission denied' error when trying to access the repository. The service account used by the pipeline has the 'Source Repository Viewer' role. What is the likely issue?

Accepted Answer

The 'Source Repository Viewer' role is insufficient; the service account needs 'Source Repository Reader' or higher. The 'Source Repository Viewer' role only allows listing and viewing repository metadata, not reading the actual source code. To clone or pull code from a Cloud Source Repository, the service account needs the 'Source Repository Reader' role (or higher), which grants the `source.repos.get` and `source.repos.read` permissions required for Git operations. The pipeline's CustomJob component fails because the service account lacks these permissions when attempting to access the repository.

Answer

The training code contains a dependency that is not available in the custom container

Answer

The pipeline is running in a different project than the repository; cross-project access is not supported

Answer

The repository URL is incorrectly formatted; use the SSH URL instead of HTTPS

Question 15

A team uses Vertex AI Feature Store with an online store. They need low-latency serving for millions of features with high write throughput. Which online store type should they choose?

Accepted Answer

Bigtable online store. Bigtable online store is optimized for high throughput and low latency, suitable for large-scale online serving.

Answer

Cloud SQL online store

Answer

Optimized online store

Answer

Firestore online store

Question 16

A team wants to deploy a model on Vertex AI Edge Manager for offline inference on edge devices. Which three steps are required? (Choose 3)

Accepted Answer

Package the model and deploy using Vertex AI Edge Manager. The model must be in a format compatible with edge devices (TFLite/ONNX), and Edge Manager requires packaging and deploying the model to the device.

Answer

Enable Vertex AI Model Monitoring

Answer

Create a Vertex AI Endpoint with HTTP endpoint

Question 17

You are deploying a model to a Vertex AI endpoint and need to minimize latency for online predictions. Which machine type should you choose?

Accepted Answer

n1-standard-2 with NVIDIA Tesla T4. GPU-enabled machines (e.g., n1-standard-2 with NVIDIA Tesla T4) accelerate compute-heavy models, reducing prediction latency significantly compared to CPU-only instances.

Answer

e2-standard-2

Answer

n1-standard-2

Answer

n1-highmem-2

Question 18

You deployed a model to a Vertex AI endpoint with minReplicas=0 and maxReplicas=5. After sending prediction requests, you notice the endpoint takes about 30 seconds to respond initially, but subsequent requests are fast. What is the most likely cause?

Accepted Answer

Cold start occurs because the endpoint scaled down to zero.. Vertex AI endpoints with minReplicas=0 scale down to zero when idle. The first request after a period of inactivity triggers a cold start, where the endpoint must provision a new VM instance and load the model, causing a ~30-second delay. Subsequent requests are fast because the instance remains warm and handles them without provisioning overhead.

Answer

The model is too large for the machine type.

Answer

The VPC Service Controls are blocking the initial request.

Answer

The endpoint's autoscaling is misconfigured.

Question 19

You are building a CI/CD pipeline for an ML model using Cloud Build. When code is pushed to the main branch, you want to automatically build a training image, run a Vertex AI pipeline, and if the model evaluation passes, deploy it to a staging endpoint. Which two components are essential for this CI/CD pipeline?

Accepted Answer

Vertex AI Pipelines to orchestrate training and evaluation.. Vertex AI Pipelines is the service that orchestrates the entire ML workflow, including training, evaluation, and conditional deployment logic. In a CI/CD pipeline, you need a managed orchestrator to chain steps like model training, evaluation, and deployment, and Vertex AI Pipelines provides that with its Kubeflow Pipelines-based DAG execution.

Answer

Cloud Scheduler to trigger the pipeline on a schedule.

Answer

Cloud Functions to deploy the model.

Answer

Vertex AI Continuous Training service.

Question 20

A data scientist has trained a scikit-learn model locally and wants to deploy it to Vertex AI for online predictions with low latency. The model is a small RandomForestClassifier (100 MB). What is the recommended way to deploy this model?

Accepted Answer

Upload the model to Vertex AI Model Registry using the pre-built scikit-learn serving container.. Vertex AI provides a pre-built container for scikit-learn that is optimized for serving predictions with low latency. For a small RandomForestClassifier (100 MB), this container handles model loading, request routing, and scaling automatically, eliminating the need for custom infrastructure. This is the recommended approach for deploying scikit-learn models to Vertex AI for online predictions.

Answer

Deploy the model on a Kubernetes cluster with Istio.

Answer

Package the model as a Docker container with a custom prediction routine.

Answer

Export the model as a TensorFlow SavedModel and use the pre-built TF serving container.