PDE Operationalizing machine learning models Practice Test 10 — 15 Questions

Question 1

A team is implementing CI/CD for their ML models using Google Cloud. They want to automatically retrain and deploy a new model version when new training data arrives in Cloud Storage. Which combination of services should they use?

Accepted Answer

Cloud Storage triggers, Cloud Functions, and Vertex AI Pipelines. Option A is correct because Cloud Storage triggers fire an event when new data arrives, which invokes a Cloud Function that can start a Vertex AI Pipeline for retraining and deploying the model. This combination provides a fully managed, event-driven CI/CD pipeline for ML models without manual intervention.

Answer

Cloud Scheduler and Vertex AI Training

Answer

Cloud Pub/Sub and Cloud Composer

Answer

Cloud Storage notifications and Cloud Build

Question 2

A team is training a large model using a custom container with TensorFlow on Vertex AI Training. They need to use multiple GPUs across several machines. Which strategy should they implement to maximize training throughput?

Accepted Answer

Use Vertex AI Training with a custom job specifying workerPoolSpecs and MultiWorkerMirroredStrategy. Vertex AI supports multi-worker distributed training with the 'distribution_strategy' argument in the custom job config. Using a single VM with multiple GPUs is limited by that machine's capabilities. The 'MirroredStrategy' addresses single-machine multi-GPU, not multi-machine.

Answer

Use Cloud TPU Pods for distributed training

Answer

Use Dataflow for distributed training

Answer

Use a single worker with multiple GPUs and TensorFlow MirroredStrategy

Question 3

Which TWO actions should you take to ensure model reliability in a production Vertex AI Endpoint?

Accepted Answer

Monitor prediction accuracy in production with logging and alerts. Monitoring prediction accuracy with logging and alerts (B) is essential for detecting model drift, data drift, and performance degradation in production. Vertex AI provides model monitoring features that automatically log prediction requests and responses, compute statistics, and trigger alerts when skew or drift thresholds are breached, enabling proactive remediation.

Answer

Use only batch predictions to avoid real-time issues

Answer

Disable request/response logging to reduce latency

Answer

Use a single model endpoint for all traffic

Question 4

Which THREE Google Cloud services are typically used together in a production ML pipeline?

Accepted Answer

Cloud Storage. Cloud Storage is correct because it serves as the central artifact repository in a production ML pipeline on Google Cloud. It stores training data, model artifacts, and prediction inputs/outputs, enabling seamless integration with Vertex AI Training for model training and Vertex AI Prediction for serving. Without Cloud Storage, there is no durable, scalable, and cost-effective way to manage the large datasets and model binaries required for production ML workflows.

Answer

Cloud Functions

Answer

BigQuery

Question 5

Which TWO strategies help reduce prediction latency for a real-time model deployed on Vertex AI Endpoint?

Accepted Answer

Reduce model complexity (e.g., quantize or prune). Enabling autoscaling with min replicas reduces cold start latency. Reducing model complexity (e.g., quantization) speeds up inference. Larger machine types may increase latency if not needed. Batch prediction is offline. Cloud CDN is for static content.

Answer

Use batch prediction instead of online

Answer

Use Cloud CDN to cache predictions

Answer

Use a larger machine type (e.g., n1-highcpu-16)

Question 6

Refer to the exhibit. What is the cause of this error?

Accepted Answer

The machine type flag is only used during model deployment, not endpoint creation. The --machine-type flag is not valid for the endpoints create command; it should be specified when deploying a model to the endpoint using 'gcloud ai endpoints deploy-model'. The user must first create an endpoint without machine type, then deploy a model.

Answer

The endpoint name already exists

Answer

The user must specify a model name

Answer

The region is missing

Question 7

Refer to the exhibit. This log entry was generated by Vertex AI Model Monitoring for a production model. What should the data engineer do to address this issue?

Accepted Answer

Retrain the model with more recent data. Option B is correct because Vertex AI Model Monitoring detected a drift in the 'age' feature, indicating that the production data distribution has shifted from the training data. Retraining the model with more recent data aligns the model with the current data distribution, mitigating the drift and maintaining prediction accuracy. This is the standard remediation for model drift in production ML systems.

Answer

Increase the drift threshold to 0.9 to suppress alerts

Answer

Deploy a new model version trained on the original dataset

Answer

Disable monitoring for the 'age' feature

Question 8

Refer to the exhibit. A team is trying to run a custom prediction container on Vertex AI Endpoint. They get this error when the container starts. What is the most likely cause?

Accepted Answer

The entry point is missing or incorrect. The error occurs when the container starts, which typically happens during the initial health check or readiness probe. Vertex AI Endpoints require a valid entry point (e.g., CMD or ENTRYPOINT in the Dockerfile) to start the prediction server. If the entry point is missing or incorrect, the container fails to launch, resulting in the observed error.

Answer

The container image is too large

Answer

The container is built for a different CPU architecture

Answer

The model file is missing from the container

Question 9

Your company has a machine learning model that predicts customer churn. The model is deployed on Vertex AI Endpoints with autoscaling. After a marketing campaign, traffic to the endpoint increases by 10x. Some predictions start failing with 'HTTP 503 Service Unavailable' errors. What is the most likely cause?

Accepted Answer

The autoscaling configuration has insufficient maximum nodes to handle the traffic.. A 503 Service Unavailable error from Vertex AI Endpoints indicates that the endpoint is overwhelmed and cannot handle the incoming request volume. With a 10x traffic spike and autoscaling configured, the most likely cause is that the autoscaling configuration has insufficient maximum nodes, so the endpoint cannot scale out enough to handle the load, causing requests to be rejected.

Answer

The model container has a memory leak.

Answer

The model's accuracy has degraded due to data drift.

Answer

The model is using an older version that is not supported.

Question 10

You are deploying a machine learning model to production using Vertex AI. The model requires GPU acceleration for low-latency predictions. You need to minimize costs while ensuring availability during a defined business hours window (8 AM to 6 PM). Which deployment strategy should you use?

Accepted Answer

Deploy to an endpoint with manual scaling, set min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours.. Option A is correct because it uses manual scaling with a cron job to set min nodes to zero outside business hours (8 AM–6 PM) and scale up to a maximum of 10 nodes during business hours, ensuring GPU availability when needed while minimizing costs by running zero instances when the model is not required. This approach directly addresses the requirement for low-latency GPU predictions during a defined window without paying for idle GPU resources outside that window.

Answer

Use a custom prediction routine (CPR) that dynamically requests GPUs from the cluster.

Answer

Deploy to a dedicated endpoint with a GPU machine and configure autoscaling.

Answer

Use Cloud Functions to invoke the model, and let Google Cloud manage the underlying GPU infrastructure.

Question 11

You are responsible for monitoring a production ML model on Vertex AI. The model predicts loan approval probability. The business team reports that the model's predictions are becoming less accurate over the last week. You check the model's monitoring dashboard and see that the prediction distribution has changed significantly. What is the most likely issue?

Accepted Answer

The model is experiencing concept drift.. The correct answer is D because concept drift occurs when the underlying relationship between input features and the target variable changes over time, causing the model's predictions to become less accurate even if the input data distribution remains stable. In this scenario, the prediction distribution has changed significantly, which is a hallmark of concept drift, as the model's learned decision boundary no longer reflects the current real-world patterns. Vertex AI's monitoring dashboard can track prediction distribution shifts, and this symptom points to concept drift rather than data drift.

Answer

The model is suffering from overfitting to the training data.

Answer

There is a bug in the model's preprocessing code.

Answer

There is data drift in the input features.

Question 12

Your team uses a CI/CD pipeline with Cloud Build to train and deploy ML models on Vertex AI. You want to ensure that only models that pass validation checks (e.g., accuracy threshold, fairness metrics) are promoted to production. What is the best way to implement this?

Accepted Answer

In the Cloud Build pipeline, after training, run validation scripts. If validation passes, deploy to a staging endpoint for manual approval, then promote to production.. Option D is correct because it integrates validation directly into the CI/CD pipeline using Cloud Build, ensuring that only models passing specific checks (e.g., accuracy threshold, fairness metrics) are promoted. By running validation scripts after training and requiring manual approval before production promotion, this approach provides both automated gatekeeping and human oversight, aligning with MLOps best practices for safe model deployment.

Answer

Use Cloud Scheduler to trigger retraining and only deploy if the new model outperforms the previous one on a holdout set.

Answer

Use Vertex AI Model Registry's automatic promotion feature that moves models to production based on evaluation results.

Answer

Configure Cloud Functions to re-evaluate the model daily and promote if it passes.

Question 13

You deployed a model on Vertex AI Endpoints using a custom container. The model serves predictions but the latency is higher than expected. You suspect the container is not making full use of the CPU resources. What should you do to reduce latency?

Accepted Answer

Modify the container to use multi-threading or increase the number of workers in the prediction server (e.g., Gunicorn workers).. Option A is correct because high latency in a CPU-based custom container often stems from underutilizing available CPU cores. By increasing the number of workers (e.g., Gunicorn workers) or enabling multi-threading, you allow the prediction server to handle multiple requests concurrently, reducing queue time and improving throughput. This directly addresses the symptom of the container not making full use of CPU resources.

Answer

Enable response caching on the endpoint.

Answer

Change the machine type to a GPU-accelerated machine.

Answer

Increase the number of nodes by adjusting autoscaling limits.

Question 14

Your organization uses Vertex AI Feature Store to serve features for a real-time fraud detection model. The model is deployed on a Vertex AI endpoint. After a data pipeline update, the model's online predictions became inconsistent. What is the most likely cause?

Accepted Answer

The feature store's online serving values are not synchronized with the batch feature values used during training.. In Vertex AI Feature Store, batch feature values used during model training and online serving values are stored separately. If a data pipeline update changes the batch feature values but the online serving values are not updated or synchronized, the model will receive different feature values at inference time than it was trained on, leading to inconsistent predictions. This is the most common cause of prediction drift after a pipeline change.

Answer

The model's prediction server is running out of memory.

Answer

The model was retrained with a different training dataset.

Answer

The online serving endpoint's model version was accidentally rolled back.

Question 15

You manage a team that deploys multiple versions of a computer vision model for A/B testing on Vertex AI Endpoints. You need to route a small percentage of traffic to a canary version while the rest goes to the stable version. You also need to gradually increase the canary traffic over time based on performance metrics. Which approach should you take?

Accepted Answer

Deploy both models to the same endpoint and configure traffic splitting percentages using the Vertex AI console or API.. Vertex AI Endpoints support traffic splitting between model versions. You can assign percentage splits and adjust them programmatically. Weighted routing in Cloud Load Balancing is lower-level. Using two separate endpoints would not allow splitting within a single endpoint. Feature flags are for application logic, not model serving.

Answer

Create two separate endpoints, one for each version, and use a separate load balancer to route a percentage of requests to the canary endpoint.

Answer

Use Cloud Armor with weighted backend services to route a portion of requests to the canary version.

Answer

Implement feature flags in the application code to randomly select the model version for each prediction request.