PMLE Practice Exam 64 — 20 Questions

Question 1

A retail company wants to predict customer churn using historical purchase data stored in BigQuery. The data includes customer demographics, transaction history, and support interactions. The team is comfortable writing SQL and wants to avoid moving data to a separate environment. Which approach should they take?

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

Accepted Answer

Use BigQuery ML to create a logistic regression model (LOGISTIC_REG) on the data directly in BigQuery.. BigQuery ML allows the team to build and train a logistic regression model directly on data stored in BigQuery using SQL syntax, without moving data to a separate environment. The LOGISTIC_REG model type is specifically designed for binary classification tasks like churn prediction, and it runs entirely within BigQuery's serverless infrastructure, satisfying the team's requirement to avoid data movement.

Answer

Use the Cloud Natural Language API to analyze customer support interactions and combine results with purchase data in BigQuery.

Answer

Export the data to a CSV file and use Vertex AI AutoML Tables to train a classification model.

Answer

Create a Dataflow pipeline to stream data to Cloud SQL and use Cloud SQL's built-in ML functions.

Question 2

A company uses Vertex AI Pipelines for ML workflows. They want to standardize pipeline templates across teams to ensure consistency. Which TWO approaches should they use?

Accepted Answer

Create reusable pipeline components using the Vertex AI SDK and store them in a shared repository. Using the Vertex AI SDK to create reusable pipeline components and storing them in a shared repository ensures consistency. Publishing components to the Google Cloud Marketplace is not a standard approach.

Answer

Use only pre-built components from Google's public repository

Answer

Share notebooks with pipeline code via Google Drive

Answer

Publish pipeline components as custom containers in Google Cloud Marketplace

Question 3

Which THREE are key capabilities of Vertex AI Feature Store?

Accepted Answer

Feature monitoring and validation to detect skew. Vertex AI Feature Store provides built-in feature monitoring and validation capabilities that detect training-serving skew and data drift. This is critical for maintaining model performance in production, as it alerts when the distribution of feature values changes between training and serving environments.

Answer

Automatic generation of feature embeddings

Answer

Real-time streaming ingestion from Apache Kafka

Question 4

You are fine-tuning a pre-trained BERT model from Hugging Face for a sentiment analysis task using Vertex AI training. The dataset has 100k examples. To avoid catastrophic forgetting, which layer freezing strategy should you apply?

Accepted Answer

Unfreeze all layers and fine-tune the entire model. For fine-tuning with a sufficiently large dataset, it is common to unfreeze all layers to adapt the model to the new task. Freezing many layers is typical for very small datasets. With 100k examples, full fine-tuning is appropriate.

Answer

Freeze the first 6 layers, fine-tune the last 6 layers

Answer

Freeze all layers except the classification head

Answer

Use transfer learning only on the embeddings layer

Question 5

A team has trained a sentiment analysis model using PyTorch on Vertex AI Training. They now want to deploy it for online predictions with low latency. Which TWO actions should they take? (Choose 2)

Accepted Answer

Use a machine type with a GPU for faster inference.. GPU-accelerated inference significantly reduces latency for deep learning models like sentiment analysis, especially when using PyTorch, which has native CUDA support. Vertex AI Prediction supports GPU machine types (e.g., n1-standard-4 with NVIDIA T4) that can process batched requests faster than CPUs, directly addressing the low-latency requirement.

Answer

Create multiple model versions for A/B testing.

Answer

Enable batch prediction instead of online prediction.

Answer

Convert the model to TensorFlow SavedModel format.

Question 6

A Vertex AI pipeline is triggered from Cloud Build using the configuration above. The pipeline fails with an error: 'Unable to submit build: The source code is not available.' What is the most likely cause?

Accepted Answer

The 'gcloud builds submit' command does not have access to the source code in the Cloud Build environment.. The error 'Unable to submit build: The source code is not available' indicates that the Cloud Build environment cannot locate the source code when the 'gcloud builds submit' command is executed. This typically happens when the pipeline is triggered from Cloud Build but the source code is not properly staged or accessible in the build context, often because the build configuration does not include the source directory or the source is not uploaded to Cloud Storage. Option B correctly identifies that the command lacks access to the source code in the Cloud Build environment.

Answer

The Docker build step failed silently due to a missing dependency.

Answer

The Docker image tag does not include a hash, causing the push to fail.

Answer

The Cloud Build service account lacks permission to access the Vertex AI Pipeline API.

Question 7

A data engineer wants to compute feature aggregates over a large dataset stored in BigQuery and write the results to Vertex AI Feature Store. The pipeline must handle both batch and streaming data. Which Google Cloud service should they use?

Accepted Answer

Cloud Dataflow with Apache Beam. Dataflow (Apache Beam) is the recommended service for both batch and streaming data processing at scale. It can read from BigQuery and write to Feature Store.

Answer

BigQuery scheduled queries

Answer

Cloud Functions triggered by Pub/Sub

Answer

Cloud Dataproc with Spark

Question 8

Refer to the exhibit. A data scientist runs the above BigQuery ML query to create a logistic regression model. After training, the model is evaluated using ML.EVALUATE. The evaluation shows poor performance with high bias. Which action would most likely improve the model's performance?

Accepted Answer

Add more complex features by including polynomial expansions.. High bias indicates the model is underfitting the data, meaning it is too simple to capture underlying patterns. Adding polynomial expansions (feature crosses) in the TRANSFORM clause increases model complexity, allowing the logistic regression to learn non-linear decision boundaries, which directly addresses underfitting.

Answer

Remove the TRANSFORM clause and use raw features.

Answer

Change the model_type to 'linear_reg'.

Answer

Increase the number of training iterations by setting MAX_ITERATIONS.

Question 9

A company is deploying a new model version to an existing Vertex AI endpoint. They want to test the new version with 5% of traffic before fully rolling it out. What is the correct approach?

Accepted Answer

Deploy the new version as a separate model on the same endpoint and use the `traffic_split` parameter in the deployment request.. Vertex AI endpoints support traffic splitting between multiple deployed models. By deploying the new model version to the same endpoint and setting `traffic_split` to 5% for the new version and 95% for the existing version, the endpoint automatically routes a corresponding proportion of inference requests to each model without any client-side changes.

Answer

Create a new endpoint for the new version and update the client to call both endpoints.

Answer

Deploy the new version and set the minimum replicas to 0, then gradually increase.

Answer

Use Cloud Load Balancing to distribute traffic between two endpoints.

Question 10

A machine learning engineer is building a pipeline with Vertex AI Pipelines and wants to pass a large dataset between components without copying it to the container's memory. What is the best practice for passing data between pipeline components?

Accepted Answer

Use Cloud Storage URIs (gs://) to point to the data location.. Vertex AI Pipelines natively supports passing Cloud Storage URIs (gs://) as artifact references between components, allowing components to read the dataset directly from GCS without copying it into container memory. This avoids memory limits and enables efficient handling of large datasets by leveraging GCS's scalable object storage.

Answer

Mount an NFS volume to all containers and share data via the filesystem.

Answer

Serialize the dataset to JSON and include it as a pipeline parameter.

Answer

Use the importer component to load the data into the pipeline as an in-memory artifact.

Question 11

A healthcare startup is building a diagnostic tool that uses a deep learning model to classify medical images. The model is trained on TensorFlow and deployed on Vertex AI Prediction. The startup has strict latency requirements: predictions must return within 200 ms for 95% of requests. Current performance shows p95 latency of 350 ms. The team has already tried using a smaller model, but accuracy dropped below acceptable levels. The traffic pattern is spiky: low load during nights but bursts of 1000 requests per second during business hours. Currently, they use a single n1-highmem-8 VM with a GPU attached. They have a budget for additional resources but need to optimize cost. The model is about 500 MB and requires GPU for inference. Which course of action should they take to meet the latency requirement while managing costs?

Accepted Answer

Create a Vertex AI Prediction endpoint with an accelerator (GPU) and enable autoscaling (min 1, max 5 nodes). It leverages Vertex AI Prediction's autoscaling to handle spiky traffic efficiently, using GPU-accelerated endpoints that can scale from 1 to 5 nodes to meet the 200 ms p95 latency requirement. This approach minimizes cost during low-load periods while providing burst capacity for the 1000 requests per second peak, addressing both the latency and budget constraints without compromising model accuracy.

Answer

Upgrade to an n1-highmem-16 VM with a more powerful GPU

Answer

Switch to batch prediction using Vertex AI Batch Prediction and store results in a database for retrieval

Answer

Deploy the model as a Cloud Function using TensorFlow Serving

Question 12

A machine learning engineer wants to deploy a trained model to Vertex AI for online predictions. Which Vertex AI resource is required to serve the model and provide an endpoint URL?

Accepted Answer

Vertex AI Endpoint. Vertex AI Endpoint is the required resource to deploy a trained model for online predictions, as it provides a dedicated endpoint URL that accepts prediction requests and routes them to the model. Without an endpoint, the model cannot be accessed via HTTP/HTTPS for real-time inference, which is the core requirement for online serving.

Answer

Vertex AI Pipeline

Answer

Vertex AI Model Registry

Answer

Vertex AI Feature Store

Question 13

The exhibit shows part of a Vertex AI Pipeline definition. The pipeline fails at the training step with an error: 'Missing required input: train_data'. What is the most likely cause?

Accepted Answer

The data_processing step does not define any outputs. The error 'Missing required input: train_data' indicates that the training step expects an input artifact named 'train_data', but no upstream step provides it. In Vertex AI Pipelines, a component's output must be explicitly defined and connected to the downstream component's input. Since the data_processing step does not define any outputs, it cannot produce the 'train_data' artifact, causing the training step to fail.

Answer

The evaluation step expects a metric output but training does not produce it

Answer

The training step uses the wrong image tag

Answer

The container command for data_processing is incorrect

Answer

The pipeline is missing a deployment step

Question 14

A healthcare startup deployed a Vertex AI AutoML Vision model to detect anomalies in medical images. The model performs well on the test set but has high latency in production, exceeding the 2-second SLA. The images are stored in Cloud Storage and are processed via a Cloud Function triggered by new uploads. What is the most likely cause?

Accepted Answer

The model is deployed on a small machine type with insufficient compute.. The most likely cause of high latency exceeding the 2-second SLA is that the Vertex AI AutoML Vision model is deployed on a small machine type (e.g., n1-standard-2 or lower) with insufficient compute resources (CPU/memory). AutoML Vision endpoints use container-based serving, and underpowered machines cannot handle the inference load efficiently, especially for high-resolution medical images, leading to response times beyond the SLA.

Answer

The images are being resized and preprocessed in the Cloud Function, adding latency.

Answer

The Cloud Function has a cold start issue.

Answer

The AutoML Vision endpoint is not using GPU acceleration.

Question 15

A company has a large dataset of labeled images (e.g., different species of plants). They want to train a custom image classification model with minimal effort and no prior ML experience. Which Google Cloud service should they use?

Accepted Answer

AutoML Vision. AutoML Vision is the correct choice because it allows users with no prior ML experience to train a custom image classification model using a simple graphical interface, requiring only labeled images as input. It automates model architecture search, hyperparameter tuning, and deployment, minimizing manual effort while delivering a production-ready model.

Answer

Cloud TPU

Answer

Vertex AI Workbench with a custom TensorFlow model

Answer

Vision API

Question 16

A company uses Vertex AI Experiments to track ML training runs. They want to enforce that all training runs use only approved libraries from a central Artifact Registry to ensure compliance. Which approach should they take?

Accepted Answer

Create a custom Vertex AI training container that installs libraries from Artifact Registry at build time and restrict training job submission to that container using IAM.. It enforces compliance at the image level: by building a custom container that installs only approved libraries from Artifact Registry at build time, and then restricting training job submission to that specific container using IAM, you ensure that no unauthorized libraries can be introduced at runtime. This approach eliminates the risk of developers injecting unapproved dependencies via startup scripts or runtime pulls, and it aligns with the principle of immutable infrastructure for ML training.

Answer

Use a startup script in the training VM to install libraries from Artifact Registry.

Answer

Use Vertex AI Pipelines with a component that pulls libraries from Artifact Registry at runtime.

Answer

Configure Vertex AI Training with a custom job configuration that specifies the library sources.

Answer

Use Cloud Build to build the training image with approved libraries and push to Container Registry, then restrict training jobs to that image.

Question 17

A company deploys an online prediction model serving 100 requests per second. They are optimizing for both latency and throughput. Which monitoring strategy should they use?

Accepted Answer

Monitor both the p50 and p99 latency, and the request count. Create a dashboard showing latency vs. throughput at different load levels.. Monitoring both p50 and p99 latency alongside request count provides a comprehensive view of system performance under load. Latency percentiles reveal tail behavior (p99) and typical user experience (p50), while request count tracks throughput. A dashboard correlating latency vs. throughput at different load levels is essential for identifying performance cliffs or degradation before failures occur, aligning with best practices for production ML inference systems.

Answer

Monitor only the request count and set an alert if it drops below a threshold.

Answer

Set a single alert on the 99th percentile latency and ignore throughput since it's already high.

Answer

Monitor the error rate and set an alert if it exceeds 1%.

Question 18

A company is fine-tuning a large language model (Gemma 7B) using Vertex AI JumpStart. They want to reduce the model's memory footprint for deployment on edge devices. Which THREE model compression techniques should they consider?

Accepted Answer

Post-training quantization to INT8. Post-training quantization (e.g., to INT8) reduces precision and size. Quantization-aware training simulates quantization during training for better accuracy. Pruning removes redundant weights. Knowledge distillation trains a smaller model. For edge deployment, quantization (both post-training and quantization-aware) and pruning are common. Distillation is also valid but often considered separate.

Answer

Using a larger batch size during inference

Answer

Increasing the number of layers

Question 19

The exhibit shows a Cloud Composer environment variable configuration. An ML pipeline DAG fails with an authentication error when trying to access Vertex AI. What is the most likely cause?

Accepted Answer

The Airflow worker does not have the proper scopes to access Vertex AI. The authentication error when accessing Vertex AI from Cloud Composer most likely occurs because the Airflow worker's service account lacks the necessary OAuth scopes or IAM permissions. Cloud Composer uses a worker service account to execute tasks; if this account does not have the `https://www.googleapis.com/auth/cloud-platform` scope or the `aiplatform.user` role, the Airflow worker cannot authenticate to Vertex AI APIs, resulting in a 403 or 401 error.

Answer

The service account key in the environment variable is expired

Answer

The DAG file is missing a required Python library

Answer

The Cloud Composer environment is in a different project than Vertex AI

Question 20

A company uses Vertex AI Predictions with a custom container that invokes an external API for feature enrichment. The prediction response time is highly variable. The engineer wants to monitor the external API's contribution to latency. What should the engineer do?

Accepted Answer

Instrument the prediction container to emit custom metrics for the time spent in each prediction step, including the external API call.. Instrumenting the custom container to emit custom metrics (e.g., using OpenTelemetry or a Prometheus client library) allows the engineer to directly measure the time spent in each prediction step, isolating the external API call's contribution to latency. This provides granular, real-time visibility into the specific bottleneck, which is essential when the response time is highly variable and the external API is a known dependency.

Answer

Add a timeout setting to the endpoint's request to limit the external API call duration.

Answer

Monitor the Vertex AI endpoint latency metric and correlate with system metrics like CPU and memory.

Answer

Use Cloud Trace to trace the prediction request end-to-end, including the external API call.