PMLE Practice Test 35 — 15 Questions

Question 1

A company is using Vertex AI Pipelines for ML workflows. They want to implement best practices for idempotent components and data passing. Which THREE practices should they adopt?

Accepted Answer

Pass large datasets between components using GCS URIs instead of in-memory values.. Vertex AI Pipelines components run in isolated containers; passing large datasets in-memory would exceed memory limits and cause failures. Using GCS URIs allows components to read/write data directly from Cloud Storage, which is the recommended pattern for handling large artifacts in Kubeflow Pipelines (the underlying orchestrator). This approach also enables caching and parallel execution since components only depend on the URI, not on the state of previous containers.

Answer

Read data into memory in the first component and pass the in-memory object to subsequent components.

Answer

Use global variables in the pipeline code to store intermediate results.

Question 2

Refer to the exhibit. This IAM policy is applied at the project level. What is the effect of the condition?

Accepted Answer

The service account can only access AI Platform resources that start with 'projects/ml-'. The condition block uses the `resource.name.startsWith` condition key to restrict access to AI Platform resources whose names begin with `projects/ml-`. This means the service account can only interact with AI Platform resources (such as models, jobs, or endpoints) that have a resource name starting with that prefix, effectively scoping the permission to a specific set of projects or resources.

Answer

The service account can only be used in projects whose ID starts with 'ml-'

Answer

The role is granted only if the project's name contains 'ml-'

Answer

The condition is ignored because conditions are not supported for service accounts

Question 3

Which Vertex AI service is best suited for finding similar items in a large dataset based on embedding vectors, such as product recommendations or image similarity search?

Accepted Answer

Vertex AI Matching Engine. Vertex AI Matching Engine is specifically designed for high-performance vector similarity search (also known as approximate nearest neighbor search) using embedding vectors. It scales to billions of vectors and is ideal for use cases like product recommendations and image similarity search, where you need to find the most similar items based on dense vector representations.

Answer

Vertex AI Prediction Endpoint

Answer

Vertex AI Model Monitoring

Answer

Vertex AI Feature Store

Question 4

You are an ML engineer at a logistics company. The company uses a Vertex AI Pipeline with BigQuery ML to train a model that predicts delivery delays based on weather, traffic, and historical order data. The pipeline runs daily and includes steps: (1) data extraction from BigQuery, (2) feature engineering using Dataflow, (3) model training with BigQuery ML (logistic regression), (4) model evaluation, and (5) conditional deployment to a Vertex AI Endpoint if accuracy > 0.85. Recently, the pipeline has been failing at step 5 with the error: "Vertex AI Endpoint creation failed: Quota limit of 1 endpoint per region exceeded." The company has already created one endpoint in the same region for another model. The pipeline is configured to create a new endpoint each time a model is deployed. The engineer needs to fix this with minimal changes to the pipeline code. Which course of action should the engineer take?

Accepted Answer

Modify the deployment step to check if an endpoint already exists and, if so, deploy a new model version to the existing endpoint instead of creating a new one.. It directly addresses the root cause: the pipeline fails because it tries to create a new endpoint each time, exceeding the regional quota of one endpoint. By modifying the deployment step to check for an existing endpoint and deploying a new model version to it, the engineer avoids quota issues without altering the pipeline's core logic or requiring external approvals. This approach leverages Vertex AI's model versioning capability, which allows multiple model versions under a single endpoint, aligning with minimal code changes.

Answer

Submit a quota increase request to Google Cloud for Vertex AI Endpoints in the current region.

Answer

Change the region in the pipeline configuration to a region with available endpoint quota.

Answer

Remove the accuracy threshold and deploy every model automatically to a pre-created endpoint.

Question 5

A user receives the error "Deployment failed due to insufficient memory. Please use a machine type with higher memory." when deploying an AutoML model. What should they do?

Accepted Answer

Use machine type n1-highmem-2. When deploying an AutoML model, memory constraints are a common cause of deployment failures. Using a machine type with higher memory, such as n1-highmem-2, helps ensure the model can be loaded and served without out-of-memory errors. The other options do not address memory requirements: changing the region does not affect compute resources, increasing the min replica count does not increase per-instance memory, and removing traffic-split flags does not resolve memory issues.

Answer

Change the region to us-west1

Answer

Increase the min-replica-count to 2

Answer

Remove the traffic-split flag

Question 6

Which THREE factors should be considered when choosing between using Vertex AI Endpoints and Cloud Run for model serving? (Choose three.)

Accepted Answer

Built-in model monitoring. The key differentiators between Vertex AI Endpoints and Cloud Run for model serving are built-in model monitoring, GPU support, and automatic scaling to zero. Vertex AI Endpoints provides built-in model monitoring, while Cloud Run does not offer this natively. GPU support is a strong differentiator: Vertex AI Endpoints natively supports GPUs, whereas Cloud Run has very limited GPU support, often making it unsuitable for GPU-dependent models. Automatic scaling to zero is a feature of Cloud Run, which can scale down to zero instances when not in use, reducing costs; Vertex AI Endpoints typically requires at least one instance, so it does not scale to zero as easily. In contrast, the complexity of model containerization and cost per request are less differentiating: both services require similar containerization effort and have comparable per-request pricing models, though cost specifics depend on usage patterns.

Answer

Complexity of model containerization

Answer

Cost per request

Question 7

The exhibit shows a Cloud Build configuration. An ML engineer wants to automate the deployment of a model to Vertex AI after training. What is missing in this config to successfully deploy the model?

Accepted Answer

A step to build the serving container image. The Cloud Build configuration shown is for training a model, but to deploy it to Vertex AI, a serving container image must be built and pushed to Artifact Registry. Vertex AI requires a custom serving container (or a prebuilt one) to host the model for predictions. Without a step to build the serving container image (e.g., using a Dockerfile that includes the model and serving dependencies), the deployment will fail because there is no runnable image to deploy to the endpoint.

Answer

A step to upload the training image to Artifact Registry

Answer

A step to run unit tests

Answer

A step to create the Vertex AI Endpoint

Question 8

A team needs to quickly create a visual interface for data exploration and model building without writing code. They want to run AutoML jobs and visualize results. Which Google Cloud tool should they use?

Accepted Answer

Vertex AI Workbench. Vertex AI Workbench provides a managed JupyterLab environment with a low-code interface for data exploration, AutoML model training, and result visualization without writing code. It integrates directly with Vertex AI's AutoML and custom training services, allowing users to run AutoML jobs and view evaluation metrics, feature importance, and predictions through its UI.

Answer

Cloud Datalab

Answer

Cloud Composer

Answer

Google Colab

Question 9

A company needs to perform sentiment analysis on streaming social media data. Which architecture should they use?

Accepted Answer

Pub/Sub → Dataflow → Natural Language API → BigQuery. Streaming social media data requires a scalable, ordered ingestion pipeline. Pub/Sub ingests the stream, Dataflow processes it in real-time (e.g., windowing, deduplication), the Natural Language API performs sentiment analysis, and BigQuery stores results for querying. This decouples ingestion from processing and storage, enabling exactly-once semantics and auto-scaling.

Answer

Dataflow → Pub/Sub → Natural Language API → BigQuery

Answer

Pub/Sub → Cloud Functions → Natural Language API → Cloud Storage

Answer

Cloud Functions → Pub/Sub → Natural Language API → BigQuery

Question 10

A data scientist runs a batch prediction job on Vertex AI using a custom container. The job processes a large JSONL file (10 GB) and fails with an out-of-memory error. The machine type is n1-standard-4 (15 GB memory). Which action should be taken to resolve the error while minimizing cost?

Accepted Answer

Use a machine type with more memory, such as n1-highmem-8 (52 GB).. The out-of-memory (OOM) error indicates the machine's memory is insufficient for the model or data processing. Upgrading to n1-highmem-8 (52 GB) directly addresses the memory shortage while minimizing cost, as high-memory machines provide more RAM without unnecessary extras like GPUs. Option A (reducing batch size) might help but is not the primary fix if the model itself is large, and cost efficiency is not improved. Option B (splitting input data into smaller files) does not reduce per-instance memory pressure and could increase latency and cost due to multiple jobs. Option C (adding a GPU) increases compute but not memory, so it does not resolve the OOM error.

Answer

Reduce the batch size in the prediction request.

Answer

Split the input data into smaller files and run multiple batch jobs.

Answer

Add a GPU accelerator to offload computation.

Question 11

Your team is using Vertex AI Feature Store for online predictions. You notice that feature values for some entities are missing in production, leading to failed predictions. Upon investigation, you find that the ingestion pipeline has been failing intermittently. What is the best immediate course of action to prevent prediction failures?

Accepted Answer

Configure default values for missing features in the feature store so that the model can fall back on them.. Configuring default values for missing features in the feature store allows the model to fall back on them, ensuring predictions can still be made during intermittent ingestion pipeline failures. Option B is incorrect because monitoring alerts notify of failures but do not prevent them. Option C is incorrect because ignoring missing features may lead to incorrect or failed predictions. Option D is incorrect because manually re-ingesting is not a sustainable solution and does not address the intermittent nature of the failure.

Answer

Set up monitoring alerts on the ingestion pipeline to get notified of failures.

Answer

Change the prediction request to ignore missing features.

Answer

Manually re-ingest all missing features by running the ingestion pipeline again.

Question 12

A data science team is deploying a large NLP model to Vertex AI for real-time inference. They notice high latency per request. Which action should they take first to reduce latency?

Accepted Answer

Use Vertex AI Model Optimization to quantize the model and deploy on a smaller machine.. It directly addresses the root cause of high latency in real-time inference: model size and compute requirements. Vertex AI Model Optimization applies quantization or pruning to reduce the model's memory footprint and computational cost, allowing it to run on a smaller, faster machine (e.g., fewer vCPUs or less GPU memory) while maintaining acceptable accuracy. This is the first step recommended by Google Cloud best practices for latency-sensitive deployments, as it reduces per-request processing time without requiring architectural changes.

Answer

Use Cloud Functions for inference.

Answer

Use model optimization techniques like quantization or pruning.

Answer

Enable autoscaling and set min replicas to 5.

Answer

Implement batch prediction instead of online prediction.

Question 13

An MLOps engineer is setting up monitoring for a deployed model on Vertex AI Endpoints. Which TWO actions are required to enable Vertex AI Model Monitoring for feature skew and drift? (Choose two.)

Accepted Answer

Enable request/response logging on the Vertex AI Endpoint. To enable model monitoring, you must enable request/response logging on the endpoint (to capture serving data) and create a monitoring job with the desired configuration.

Answer

Export ground truth labels to Cloud Storage

Answer

Enable Vertex AI Pipelines to run scheduled monitoring

Answer

Deploy the model with an explanation spec

Question 14

A company needs to perform real-time similarity search on a dataset of 10 million embedding vectors. They expect low latency (under 10ms) and high throughput. Which index type should they use in Vertex AI Vector Search?

Accepted Answer

Approximate nearest neighbor (ANN) index with ScaNN. For large datasets requiring low latency, an approximate nearest neighbor (ANN) index is appropriate. The Scann algorithm (ScaNN) is used by Vertex AI Vector Search for ANN.

Answer

Brute-force index

Answer

Hash-based index

Answer

Tree-based index

Question 15

A data engineer wants to use BigQuery ML to train a model for predicting customer churn (binary classification) using a large dataset. They want the model to be automatically tuned. Which model type should they choose?

Accepted Answer

AUTOML_CLASSIFIER. (AUTOML_CLASSIFIER) is correct because it automatically performs architecture search and hyperparameter tuning to find the best model for binary classification tasks, such as customer churn prediction. This is ideal when the data engineer wants the model to be automatically tuned without manual intervention, as AutoML handles feature engineering, model selection, and tuning under the hood.

Answer

LOGISTIC_REG

Answer

BOOSTED_TREE_CLASSIFIER

Answer

DNN_CLASSIFIER