PMLE Practice Exam 56 — 20 Questions

Question 1

An ML team wants to deploy multiple models (e.g., a recommender and a classifier) behind a single Vertex AI endpoint. The models have different resource requirements: the recommender needs GPU, the classifier needs high memory. How should they configure the endpoint?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Deploy both models to the same endpoint with different machine types per deployed model.. Vertex AI allows deploying multiple models on the same endpoint, each with its own machine type and resources. Traffic splitting routes requests to the correct model.

Answer

Use Cloud Run for one model and Vertex AI for the other.

Answer

Use a single machine type that meets the highest requirements.

Answer

Create separate endpoints for each model.

Question 2

A team of ML engineers is collaborating on a project using Vertex AI. They want to ensure that only approved models are deployed to production. Which approach should they use?

Accepted Answer

Use Vertex AI Model Registry with version aliases to manage model versions and promote them after approval.. Vertex AI Model Registry provides a centralized repository for managing model versions, with support for version aliases (e.g., 'champion', 'challenger') that allow teams to promote models to production only after approval. This ensures governance and traceability, meeting the requirement that only approved models are deployed.

Answer

Store all models in a Cloud Storage bucket and manually control access via IAM permissions.

Answer

Deploy models directly from training jobs to an endpoint without version tracking.

Answer

Use Cloud Dataflow to transform raw predictions and then store them in BigQuery for analysis.

Question 3

A financial services company uses Vertex AI to build credit risk models. They have a team of 10 data scientists and 3 ML engineers. They use multiple notebooks in Vertex AI Workbench, storing data in Cloud Storage and BigQuery. The team reports that training jobs sometimes fail with 'Permission denied' errors when reading from certain Cloud Storage buckets. The error occurs intermittently and only for some users. The team uses custom service accounts for each user's notebook instance, but the permissions seem inconsistent. The IT security team has enforced that all service accounts must have least privilege. What is the most effective course of action to resolve the permission issues while maintaining security?

Accepted Answer

Implement resource-level IAM policies on the specific Cloud Storage buckets used, and audit the existing service account permissions.. Implementing resource-level IAM policies on the specific Cloud Storage buckets ensures that only the necessary permissions are granted, adhering to least privilege. Auditing existing service account permissions helps identify inconsistencies and ensure proper configuration. Option A is incorrect because a single service account with broad permissions violates least privilege and centralizes risk. Option C is incorrect because granting Storage Admin is an overly permissive role. Option D is incorrect because moving data to BigQuery does not address the core permission issue and may introduce architectural complexity.

Answer

Create a single service account with broad permissions for all notebook instances and have users impersonate it.

Answer

Grant all data scientists the 'Storage Admin' role on the project to ensure they can access any bucket.

Answer

Move all training data to BigQuery to avoid Cloud Storage permission issues.

Question 4

Drag and drop the steps to create and deploy a custom ML model on Vertex AI using a container in the correct order.

Accepted Answer

1. Build and push the container, 2. Register the model, 3. Deploy to an endpoint, 4. Test. The correct order to create and deploy a custom ML model on Vertex AI using a container is: First, build and push the container image to Artifact Registry. Next, register the model in Vertex AI Model Registry. Then, deploy the model to an endpoint using Vertex AI Endpoints. Finally, test the endpoint by sending prediction requests to verify it works.

Answer

1. Register the model, 2. Build and push the container, 3. Deploy to an endpoint, 4. Test

Answer

1. Build and push the container, 2. Deploy to an endpoint, 3. Register the model, 4. Test

Answer

1. Build and push the container, 2. Register the model, 3. Test, 4. Deploy to an endpoint

Question 5

An organization wants to use Vertex AI JumpStart to fine-tune a foundation model for a custom classification task. They have a labeled dataset stored in BigQuery. Which steps should they take?

Accepted Answer

Use the Vertex AI console to select a model from JumpStart, specify the BigQuery table as the source, and launch fine-tuning.. JumpStart fine-tuning typically involves selecting a model, connecting to your dataset (often via BigQuery), configuring training, and launching. The process is largely GUI-based.

Answer

Export the data from BigQuery to CSV files in Cloud Storage, then upload to JumpStart.

Answer

Write a custom training script using PyTorch and submit to Vertex AI Training.

Answer

Use Vertex AI Model Garden to deploy the model directly without fine-tuning.

Question 6

Refer to the exhibit. What is being configured on Vertex AI?

Accepted Answer

A Vertex AI endpoint with autoscaling based on request count. The exhibit shows a Vertex AI endpoint autoscaling configuration that uses the metric 'prediction/online/requests' as the target metric. This is the standard method for enabling autoscaling based on request count, where the scaling policy adjusts the number of instances to maintain a target number of requests per instance. Option C is correct because the configuration explicitly sets the target tracking metric to 'prediction/online/requests', which triggers scaling based on request count, not CPU utilization.

Answer

A Vertex AI model training pipeline

Answer

A Vertex AI batch prediction job

Answer

A Vertex AI endpoint with autoscaling based on CPU utilization

Question 7

A company wants to build a product recommendation engine for their e-commerce website. They have historical purchase data and user interaction logs. They want a managed service that can quickly generate personalized recommendations without building custom models. Which service should they use?

Accepted Answer

Recommendations AI. Recommendations AI is a managed service specifically for retail recommendation use cases. It offers pre-built models like 'recommended-for-you' and 'frequently-bought-together'. BigQuery ML would require custom model building, and AutoML Tables is for general tabular data, not specifically for recommendations.

Answer

Dataflow with TensorFlow

Answer

BigQuery ML with MATRIX_FACTORIZATION

Answer

AutoML Tables

Question 8

You are developing a Vertex AI pipeline that runs multiple parallel training jobs with different hyperparameters, then collects their results and selects the best model. Which KFP SDK v2 construct should you use to run the parallel training tasks?

Accepted Answer

dsl.ParallelFor. In KFP SDK v2, `dsl.ParallelFor` is used to run parallel training tasks with different hyperparameters by iterating over a list of parameters and executing a pipeline component for each item in parallel. This construct enables the pipeline to run multiple branches concurrently. After parallel execution, `dsl.Collected` can gather the outputs for aggregation, but the question asks for the construct to *run* the parallel training tasks, not to collect results.

Answer

dsl.Metrics

Answer

dsl.If

Answer

dsl.Collected

Question 9

Which TWO actions are best practices when scaling a prototype ML model to production in Google Cloud?

Accepted Answer

Store and manage features in a feature store like Vertex AI Feature Store.. Vertex AI Feature Store centralizes feature management, ensuring consistency between training and serving. This eliminates training-serving skew by providing a single source of truth for features, which is critical when scaling from prototype to production.

Answer

Test the model only on a small sample of the production data to save costs.

Answer

Manually scale inference instances based on historical traffic patterns.

Answer

Use one-hot encoding for all categorical features without considering cardinality.

Question 10

You want to use Vertex AI JumpStart to quickly deploy a pre-built foundation model for text summarization. Which action is required?

Accepted Answer

Select the model from Model Garden and deploy it to a Vertex AI endpoint. JumpStart provides one-click deployment of foundation models from Model Garden. You select a model and deploy it to an endpoint. No custom training or container building is needed.

Answer

Train the model from scratch using Vertex AI Training

Answer

Export the model to a Cloud Storage bucket and use batch prediction

Answer

Build a custom Docker container with the model and deploy to Vertex AI

Question 11

You are deploying a deep learning model on edge devices with limited computational resources. The model must run inference in <10 ms and the model size must be under 50 MB. Currently, your trained model is 200 MB and runs in 50 ms. Which combination of model compression techniques should you apply?

Accepted Answer

Apply post-training quantization (INT8) and pruning. Post-training quantization to INT8 reduces model size by 4x and often speeds up inference. Pruning removes redundant weights, further reducing size. Knowledge distillation would require retraining a smaller student model. Quantization-aware training is more accurate but needs retraining. For a simple fix, quantization and pruning are effective.

Answer

Only apply weight pruning

Answer

Apply quantization-aware training and knowledge distillation

Answer

Use knowledge distillation to train a smaller student model

Question 12

You are fine-tuning a large language model using Vertex AI Training with spot VMs to reduce cost. Your training job keeps getting preempted, causing delays. Which THREE strategies can help mitigate the impact of preemption?

Accepted Answer

Enable checkpointing and restore from the latest checkpoint after preemption. Checkpointing saves progress; using a smaller model reduces training time; increasing number of workers allows faster training and recovery. Using dedicated VMs increases cost. Reducing batch size doesn't help with preemption frequency.

Answer

Reduce batch size to lower memory usage

Answer

Switch to dedicated (non-preemptible) VMs

Question 13

A retail company uses Vertex AI Tabular (AutoML Tables) to build a customer churn prediction model. The training dataset contains 50,000 rows and 30 features, with a 5% churn rate. The model achieves an AUC of 0.85 on the test set. When deployed for online predictions, the average latency is 800ms, while the business requirement is under 200ms. The engineer has already reduced the feature set to 10 features, but latency only dropped to 600ms. The model size is 2GB. The endpoint is in us-central1 using an n1-standard-4 machine with minReplicaCount=1. What should the engineer do to meet the latency requirement?

Accepted Answer

Enable model compression in Vertex AI Tabular.. Vertex AI Tabular (AutoML Tables) supports model compression, which reduces model size and inference latency by applying techniques like quantization and pruning. Since the model is 2GB and latency is 600ms (still above the 200ms target), enabling compression can shrink the model significantly, often cutting latency by 2-3x, directly meeting the requirement without changing infrastructure or converting to a different framework.

Answer

Move the endpoint to a region geographically closer to the majority of customers.

Answer

Use a larger machine type (e.g., n1-highmem-8) for the endpoint.

Answer

Convert the model to a custom TensorFlow Lite model and deploy it.

Question 14

A team wants to share a trained model with other teams within the organization. They need to provide access to the model artifact in Vertex AI Model Registry and ensure that only authorized teams can deploy the model. What should they do?

Accepted Answer

Use IAM to grant the 'aiplatform.models.deploy' role to the other teams on the model resource. Vertex AI Model Registry uses IAM to control access to model resources. By granting the 'aiplatform.models.deploy' role on the specific model resource, you ensure that only authorized teams can deploy the model, while other operations (like viewing or updating) remain restricted. This follows the principle of least privilege and avoids exposing the model artifact broadly.

Answer

Grant the other teams access to the Cloud Storage bucket where the model is stored

Answer

Set the model to public in Vertex AI Model Registry

Answer

Use Cloud Key Management Service to encrypt the model and share the decryption key

Question 15

An ML engineer is building a pipeline that includes a step to run a BigQuery query and pass the results to the next step. They want to use a pre-built Google Cloud Pipeline Component for BigQuery. Which component should they use to execute a query and output the results to a destination table?

Accepted Answer

BigQueryExecuteQuery. The correct component is BigQueryExecuteQuery because it is the pre-built Google Cloud Pipeline Component (from the `google-cloud-pipeline-components` package) specifically designed to run a BigQuery SQL query and write the results to a destination table. It returns a `DatasetArtifact` or `Table` artifact that can be passed to downstream pipeline steps, fulfilling the requirement of outputting results to a destination table.

Answer

BigQueryExportData

Answer

BigQueryQueryJobOp

Answer

BigqueryRunQuery

Question 16

A company uses AutoML Tables to predict customer churn. The model's AUC is low. Which action is most likely to improve performance?

Accepted Answer

Add more training data. Adding more training data often helps improve model performance. Increasing the training budget alone may not help if data is insufficient. Removing features with low importance could hurt. Changing the optimization objective may not directly improve AUC.

Answer

Use a different optimization objective

Answer

Increase the training budget to 10 hours

Answer

Remove features with low importance

Question 17

An engineer is using TensorFlow Transform (tf.Transform) to preprocess training data. They want to ensure that the same preprocessing logic is applied during inference without code duplication. Which approach should they take?

Accepted Answer

Use tf.Transform to generate a transform_fn and save it as a SavedModel; then use tf.saved_model.load to apply it in the serving pipeline. TensorFlow Transform outputs a SavedModel that contains the preprocessing graph. This can be exported as a transform_fn and embedded in the serving model, ensuring consistency between training and serving.

Answer

Use tf.Transform at prediction time by running a separate Beam pipeline

Answer

Use Dataflow to preprocess data for both training and serving

Answer

Write separate preprocessing code for training and serving in Python

Question 18

Refer to the exhibit. What does this query return?

Accepted Answer

The average latency per minute for the model. The query uses the `rate` function to calculate the per-second rate of increase of the `latency_seconds` counter, and then applies the `avg` aggregator to compute the average latency across all instances over the specified time range. The `by (model)` clause groups the result by the `model` label, so the output is the average latency per minute for each model. This is why option D is correct.

Answer

The maximum latency per minute

Answer

The error rate per minute

Answer

The total number of predictions per minute

Question 19

You are designing a distributed training job for a PyTorch model on Vertex AI using multiple machines with GPUs. Which TWO configurations are required to enable data parallelism with PyTorch DDP? (Choose 2.)

Accepted Answer

Use the command 'torch.distributed.launch' to start each worker.. PyTorch DDP requires the master address and port (MASTER_ADDR, MASTER_PORT) for the communication group, and WORLD_SIZE and RANK. Vertex AI sets TF_CONFIG for TensorFlow, not PyTorch. NCCL is the backend.

Answer

Enable Vertex Explainable AI during training.

Answer

Set environment variable TF_CONFIG for each replica.

Answer

Specify a custom service account with access to Cloud TPU.

Question 20

A pipeline includes a component that produces a model artifact. The team wants to automatically detect skew between the training data distribution and the serving data distribution. Which three best practices should they implement? (Choose three.)

Accepted Answer

Compare statistics using a dedicated component and alert on threshold exceedance. To detect skew, one should pass training and serving data statistics as artifacts, compare them using a statistics comparison component, and set up an alert if skew exceeds a threshold. Using GCS URIs for passing data is a general best practice for idempotency.

Answer

Use in-memory data passing for efficiency

Answer

Disable caching to ensure fresh statistics