PMLE Practice Test 28 — 15 Questions

Question 1

A team deployed a prototype classification model to Vertex AI Prediction. After a week, they notice the metrics shown in the exhibit. What is the most likely cause of the performance degradation and latency increase?

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

Accepted Answer

The training data does not represent the current production data distribution, causing the model to make incorrect predictions and requiring more computation.. The exhibit shows both accuracy degradation and increased latency. Option C is correct because when the production data distribution shifts away from the training data (data drift), the model makes more incorrect predictions, which can trigger additional computation (e.g., retries, fallback logic, or increased uncertainty estimation) and cause latency spikes. Vertex AI Prediction does not inherently add computation for wrong predictions, but the model's internal confidence thresholds or post-processing steps may consume extra resources when handling out-of-distribution inputs.

Answer

The prediction endpoint's autoscaling is too slow, causing requests to queue and time out.

Answer

The prediction requests are too large, exceeding the maximum request size limit for Vertex AI.

Answer

The custom prediction container uses outdated libraries that are incompatible with Vertex AI's runtime.

Question 2

A company has a large-scale ML system that uses Vertex AI Pipelines to retrain models weekly. The pipeline includes a custom training job and a batch prediction step. After moving to production, they observe that batch prediction jobs often fail with 'Quota exceeded' errors. The project has sufficient CPU quota. What is the most likely cause?

Accepted Answer

The batch prediction job is requesting a specific accelerator type that has a separate quota limit.. The most likely cause is that the batch prediction job is requesting a specific accelerator type (e.g., GPU or TPU) that has a separate quota limit from CPU quota. In Vertex AI, accelerator quotas are distinct from general compute (CPU) quotas, and even if the project has sufficient CPU quota, the accelerator quota may be exhausted, causing 'Quota exceeded' errors.

Answer

The pipeline is exceeding the maximum number of concurrent pipeline runs.

Answer

The batch prediction job is using a machine type that is not available in the region.

Answer

The custom training job is consuming all available quota before the batch prediction job starts.

Question 3

Refer to the exhibit. A team leader applies this IAM policy on a Vertex AI model resource. What does the condition accomplish?

Accepted Answer

Limits access to models whose resource name starts with 'dev-'. The condition in the IAM policy uses the `resource.name.startsWith('dev-')` condition expression, which restricts access to Vertex AI model resources whose resource name begins with the prefix 'dev-'. This is a common pattern for environment-based access control, allowing the data scientist to only interact with models designated for development.

Answer

Allows the data scientist to access model evaluations only

Answer

Limits access to models owned by the data scientist

Answer

Limits access to models only in the us-central1 region

Answer

Limits access to models created after a certain date

Question 4

Drag and drop the steps to set up a feature store for ML features using Vertex AI Feature Store in the correct order.

Accepted Answer

Define entity type and features, then ingest data, then serve, then monitor.. The correct sequence to set up a feature store using Vertex AI Feature Store is: first define the entity type and its features (schema), then ingest feature data into the store, then serve those features to models for predictions, and finally monitor the store for data quality, freshness, and drift. This ensures a logical flow from definition to consumption to observability.

Answer

Ingest data, then define entity type and features, then serve, then monitor.

Answer

Define entity type and features, then serve, then ingest data, then monitor.

Answer

Monitor, then define entity type and features, then ingest data, then serve.

Question 5

A company deploys an AutoML Vision model for real-time defect detection. They notice high inference latency during peak hours. Which configuration change can help?

Accepted Answer

Increase the number of max replicas. Increasing the number of max replicas allows the AutoML Vision endpoint to scale horizontally during peak hours, distributing the inference load across more compute instances. This directly reduces per-request latency by preventing queuing and resource contention, as the Vertex AI Prediction service can spin up additional replicas up to the configured maximum to handle higher throughput.

Answer

Reduce the model's input resolution

Answer

Use batch prediction

Answer

Enable model compression

Question 6

A healthcare startup is using Vertex AI to train a deep learning model for detecting anomalies in chest X-rays. The training dataset is 500 GB of images stored in Cloud Storage (GCS). They use a custom training container with TPU v3-32. The training job completes successfully, but the model performance is poor. On investigation, they discover that the input images were not preprocessed correctly: the images were resized to 256x256 instead of the required 512x512. They need to fix the preprocessing and retrain as quickly as possible. The preprocessing pipeline involves decompressing, resizing, normalizing, and augmenting images. They have a small team and limited time. Which approach should they take?

Accepted Answer

Use Dataflow with Apache Beam to build a parallel preprocessing pipeline. Dataflow with Apache Beam provides a fully managed, serverless, and highly parallel preprocessing pipeline that can efficiently process 500 GB of images in Cloud Storage. This approach decouples preprocessing from training, allowing the team to fix the resize step (256x256 to 512x512) and run the pipeline independently, then feed the corrected data into a new training job. Dataflow automatically scales resources to handle large datasets, minimizing retraining time without requiring infrastructure management.

Answer

Use Vertex AI Batch Transform to preprocess the images

Answer

Run another Vertex AI Training job with a modified container that preprocesses and trains

Answer

Use Cloud Data Fusion to orchestrate the preprocessing steps

Question 7

A large e-commerce company uses Vertex AI Pipelines to orchestrate its recommendation model training. The pipeline has several parallel components: feature engineering, model training, and model evaluation. Recently, they noticed that the pipeline often fails due to resource exhaustion in the Vertex AI custom training job for the model training component. The training job consumes significant memory and occasionally exceeds the allocated memory limit, causing the pod to be OOMKilled. The team has already increased the memory to the maximum allowed for the chosen machine type. They need to prevent the pipeline from failing while still using the same machine type. Which approach should they take?

Accepted Answer

Split the training component into multiple smaller steps that process data in chunks to reduce peak memory usage.. Splitting the training component into smaller steps that process data in chunks directly addresses the root cause of OOMKilled failures—peak memory usage exceeding the allocated limit. By reducing the memory footprint per step, the pipeline can stay within the maximum memory of the existing machine type without requiring a larger instance. This approach aligns with best practices for Vertex AI custom training jobs, where resource limits are fixed per machine type and cannot be exceeded.

Answer

Use a larger machine type with more memory to accommodate the peaks.

Answer

Add a memory check step before training that estimates memory usage and skips training if it exceeds the limit.

Answer

Implement a retry policy with exponential backoff for the training component, so it automatically retries on failure.

Question 8

Your team manages multiple ML models in Vertex AI Model Registry. Each model has several versions deployed to different endpoints for testing and production. You need to implement a process where a model version can be promoted from a staging environment to production only after it has passed automated validation tests and been approved by a designated reviewer. The team uses CI/CD pipelines (Cloud Build) for training and deployment. Currently, model versions are deployed to endpoints using Vertex AI Endpoints with a single traffic split configuration. You want to track promotion requests and enforce approval gates. What should you do?

Accepted Answer

Use Vertex AI Model Registry version aliases ('staging', 'production') and configure Cloud Build to trigger a Cloud Run service that handles approval logic, then update the alias upon approval.. Vertex AI Model Registry version aliases (e.g., 'staging', 'production') are designed to track model version lifecycle stages. By integrating Cloud Build to trigger a Cloud Run service that enforces approval logic before updating the alias, you create a clear promotion gate. This approach natively supports tracking promotion requests and enforcing approval without custom databases or manual scripts, aligning with CI/CD best practices.

Answer

Deploy each model version to a separate endpoint, and use a custom database to track which endpoint is 'production'. Then use migration scripts to switch traffic.

Answer

Store the model version metadata in a BigQuery table and use a scheduled query to automatically update the endpoint deployment based on validation results.

Answer

Use Vertex AI Model Registry labels to mark versions as 'staging' or 'production', and create a Cloud Function that checks the label before deploying to the endpoint.

Question 9

A global retailer has deployed a real-time product recommendation model on Vertex AI Endpoints. The model is a large neural network that runs on a single node with 8 vCPUs and 30 GB memory. Over the past week, the p99 latency has increased from 200ms to 2 seconds, and the error rate has risen to 5%. Cloud Monitoring shows that the endpoint's CPU utilization is consistently near 100%, and memory is at 80%. The ML engineer suspects the model is too large for the node, but model size has not changed. Logs show no increase in request volume (steady at 50 QPS). There are no recent model updates. The engineer has tried to increase the node to 16 vCPUs, but latency decreased only slightly. What is the most likely root cause and the best first step to resolve it?

Accepted Answer

Profile the inference code to identify inefficient operations, such as unnecessary copies or suboptimal batch processing, and optimize the model serving logic.. The p99 latency spike and high CPU utilization despite unchanged model size and request volume indicate a software bottleneck, not a hardware one. Profiling the inference code (Option A) can reveal inefficient operations like unnecessary data copies or suboptimal batch processing that degrade performance on the existing node. Since increasing vCPUs barely helped, the root cause is likely within the serving logic, not the compute capacity.

Answer

Add more nodes to the endpoint by enabling autoscaling to distribute the load.

Answer

Retrain the model with a smaller architecture to reduce inference time.

Answer

Move the model to a machine type with more CPU cores and a GPU to accelerate inference.

Question 10

Which THREE actions can help improve the performance of a BigQuery ML model?

Accepted Answer

Increase the amount of training data. Increasing the amount of training data provides the model with more examples to learn from, which can reduce overfitting and improve generalization, especially for complex patterns. In BigQuery ML, more data often leads to better feature representation and higher accuracy, as long as the data is clean and relevant.

Answer

Replace the model with an AutoML model via export

Answer

Increase the time interval for prediction

Question 11

A team is using Vertex AI Feature Store to manage features for training and serving. They want to monitor the freshness of the features (i.e., how recently each feature was updated). Which approach should they take?

Accepted Answer

Create a custom Cloud Monitoring metric based on feature ingestion timestamps. Vertex AI Feature Store does not provide a built-in monitoring dashboard for feature freshness. To track how recently each feature was updated, you must create a custom Cloud Monitoring metric based on feature ingestion timestamps, which allows you to define alerting thresholds and visualize freshness over time.

Answer

Use Cloud Logging to track feature updates

Answer

Use Vertex AI Feature Store's monitoring dashboard

Answer

Use Cloud Audit Logs to monitor API calls

Question 12

A team has deployed a model with autoscaling configured as shown. They notice that during off-peak hours, the endpoint consistently runs 3 instances instead of scaling down to 1. What is the most likely cause?

Accepted Answer

There is a sustained request rate that prevents scaling down.. The autoscaling configuration is likely based on a target metric (e.g., requests per second or CPU utilization). During off-peak hours, if there is a sustained but low request rate that still exceeds the scale-down threshold, the model will not reduce instances below the number needed to handle that load. The endpoint runs 3 instances because the sustained request rate prevents the scaling-down logic from triggering, even though the traffic is lower than peak.

Answer

The `enableAccessLogging` flag increases resource usage.

Answer

The `minReplicaCount` is set too high.

Answer

The model is too large to fit on a single instance.

Question 13

A data science team uses TFX to train and deploy a model on Vertex AI. They want automated monitoring for pipeline health. Which set of metrics should they monitor to quickly detect issues in the training pipeline?

Accepted Answer

Pipeline execution status (success/failure), component completion times, and data validation anomalies.. The question specifically asks about monitoring the training pipeline's health, not the serving infrastructure. Pipeline execution status directly indicates whether the pipeline ran successfully, component completion times help identify bottlenecks or failures, and data validation anomalies catch data quality issues early in the pipeline — all of which are essential for detecting issues in the training pipeline itself.

Answer

Prediction request count, latency, and error rate on the serving endpoint.

Answer

Number of pipeline runs, average CPU utilization, and memory usage.

Answer

Model accuracy, precision, and recall on the evaluation dataset.

Question 14

An MLOps team wants to automate the retraining of a model each time new data arrives in a BigQuery table. What is the most efficient Google Cloud service to orchestrate this pipeline?

Accepted Answer

Vertex AI Pipelines with a schedule trigger. Vertex AI Pipelines is purpose-built for orchestrating ML workflows, including model retraining. It integrates natively with BigQuery for data ingestion and supports schedule triggers to automate retraining upon new data arrival, making it the most efficient and managed option for this ML-specific task.

Answer

Cloud Composer with an Airflow DAG

Answer

Dataflow pipeline with a periodic trigger

Answer

Cloud Functions triggered by BigQuery events

Question 15

An ML team wants to monitor their recommendation model for fairness. Which TWO metrics should they track to detect potential bias? (Select TWO.)

Accepted Answer

Pair-wise fairness metrics such as equal opportunity difference.. Pair-wise fairness metrics like equal opportunity difference directly compare model outcomes (e.g., true positive rates) across sensitive groups, making them a standard tool for detecting bias in classification tasks. This metric measures the difference in true positive rates between privileged and unprivileged groups, where a value close to zero indicates fairness. Tracking such metrics aligns with the core principle of monitoring for disparate impact in ML systems.

Answer

Recall for the minority group only.

Answer

Overall accuracy on the test set.

Answer

Average prediction confidence per request.