PMLE Practice Exam 57 — 20 Questions

Question 1

A data engineering team needs to compute rolling window features (7-day average, 30-day sum) from a high-volume stream of e-commerce events stored in BigQuery. They must output the features to Vertex AI Feature Store for online serving. Which approach is MOST cost-effective and scalable?

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

Accepted Answer

Use Dataflow with Apache Beam, reading from BigQuery, computing windowed aggregations, and writing to Vertex AI Feature Store. Dataflow (Apache Beam) is ideal for processing large-scale batch and streaming data. It can read from BigQuery, perform windowing computations, and write to Feature Store's online store. Cloud Functions have timeouts, Cloud Composer is not optimal for streaming, and BigQuery scheduled queries are not designed for streaming-feature computation.

Answer

Use Cloud Composer (Airflow) with a daily DAG to run SQL queries on BigQuery and export results

Answer

Schedule a query in BigQuery using scheduled queries and export results to Feature Store

Answer

Use Cloud Functions triggered by Pub/Sub to compute features on the fly

Question 2

You are using tf.Transform to preprocess data at scale. Which TWO services are required to run tf.Transform on Google Cloud? (Choose 2)

Accepted Answer

Dataflow. tf.Transform requires Apache Beam for execution, which on GCP is typically run on Dataflow. The processed data and transform artifacts are stored in Cloud Storage.

Answer

Cloud Functions

Answer

Vertex AI Training

Answer

BigQuery

Question 3

Which TWO statements about Vertex AI Feature Store are correct? (Choose 2)

Accepted Answer

Feature Store provides a centralized repository for feature data.. Vertex AI Feature Store is designed as a centralized repository that organizes, stores, and serves feature data consistently across different models and pipelines. This centralization ensures feature reuse, consistency, and governance, preventing data silos and duplication across the ML lifecycle.

Answer

Feature Store automatically applies feature engineering transformations.

Answer

Feature Store can only store numerical features.

Answer

Feature Store can only be used with Vertex AI models.

Question 4

You are building a machine learning pipeline on Google Cloud. You need to perform feature engineering on large datasets stored in BigQuery and store the resulting features in Vertex AI Feature Store for both online and offline use. Which TWO Google Cloud services should you use?

Accepted Answer

Dataflow. Dataflow can read from BigQuery, compute features via Apache Beam, and write to Feature Store. Alternatively, Dataproc can also do this but Dataflow is more serverless. Cloud Functions is not suitable for large-scale. Cloud Build is for CI/CD. BigQuery ML is for in-database ML.

Answer

Cloud Functions

Answer

BigQuery ML

Answer

Cloud Build

Question 5

An ML team is using Vertex AI Online Prediction and wants to receive alerts when the 99th percentile latency exceeds 500ms for more than 5 minutes. What is the best practice to set up this alert in Cloud Monitoring?

Accepted Answer

Use the 'aiplatform.googleapis.com/prediction/online_prediction_latencies' metric with a metric threshold condition set to 500ms and a percentile aligner of 99.. Cloud Monitoring provides a pre-built metric, `aiplatform.googleapis.com/prediction/online_prediction_latencies`, which directly captures prediction latency. By applying a percentile aligner of 99 and a metric threshold condition of 500ms, you can alert when the 99th percentile latency exceeds 500ms for the specified duration, without needing custom instrumentation or external processing.

Answer

Create a custom metric from the prediction container that emits latency percentiles, then set an alert on that metric.

Answer

Use a log-based metric to parse latency from Cloud Logging and alert when the average exceeds 500ms.

Answer

Export prediction latency logs to BigQuery and run a scheduled query to check the 99th percentile, then trigger a Cloud Function to send an alert.

Question 6

You have a champion model serving 100% traffic on a Vertex AI endpoint. You want to deploy a challenger model and gradually shift 10% of traffic to it for A/B testing. What is the correct approach?

Accepted Answer

Deploy the challenger on the same endpoint and use the traffic split parameter to allocate 10% traffic to it.. Vertex AI endpoints support traffic splitting by deploying multiple model versions and assigning traffic percentages. You deploy the challenger as a new deployed model on the same endpoint and set traffic split: champion 90%, challenger 10%.

Answer

Use Cloud Run to deploy both models and use Cloud Endpoints for traffic splitting.

Answer

Deploy the challenger on a separate endpoint and use Cloud Armor to split traffic.

Answer

Create a new endpoint for the challenger and route 10% of requests via a load balancer.

Question 7

A company wants to log all prediction requests and responses from a Vertex AI Endpoint to BigQuery for auditing and debugging. How can they achieve this?

Accepted Answer

Enable request/response logging on the endpoint and create a BigQuery sink for the log.. Vertex AI endpoints can be configured to enable request/response logging. The logs can be sent to a BigQuery table via a log sink.

Answer

Export endpoint logs from Cloud Logging to Cloud Storage and then load into BigQuery manually.

Answer

Use a Cloud Function to intercept predictions and write to BigQuery.

Answer

Vertex AI endpoints do not support request/response logging.

Question 8

A company has a TensorFlow model that uses custom operations compiled as .so files. They want to deploy it on Vertex AI for online predictions. The model runs correctly when loaded locally. However, on Vertex AI, the prediction fails with a 'Op type not registered' error. What is the most likely reason?

Accepted Answer

The custom ops were compiled for a different CPU architecture.. Custom TensorFlow operations compiled as .so files are architecture-specific. If the local machine uses a different CPU architecture (e.g., x86_64 with AVX2) than the Vertex AI serving nodes (e.g., x86_64 without AVX2 or ARM), the dynamic library will fail to load, causing the 'Op type not registered' error. The model runs locally because the ops are available, but on Vertex AI the shared object cannot be loaded, so TensorFlow cannot register the custom kernels.

Answer

The model is using a deprecated TensorFlow version.

Answer

The custom ops are not included in the model directory.

Answer

The prediction request format is incorrect.

Question 9

A company needs to serve a model with strict latency requirements (<100ms). They are using Vertex AI Prediction with CPU. During testing, latency is 150ms. What should they do?

Accepted Answer

Switch to a GPU machine type. The model's latency of 150ms exceeds the 100ms requirement. Switching to a GPU machine type (Option D) is correct because GPUs are optimized for parallel computation, significantly reducing inference latency for many ML models, especially deep learning models, compared to CPUs. Vertex AI Prediction supports GPU machine types, and this change directly addresses the latency bottleneck without altering the model or its serving configuration.

Answer

Enable batching to improve throughput

Answer

Use a smaller machine type with more replicas

Answer

Export the model to TensorFlow Lite

Question 10

A data analyst wants to train a binary classification model on a BigQuery table without moving data out of BigQuery. They have limited ML expertise. Which approach should they take?

Accepted Answer

Use BigQuery ML with CREATE MODEL and LOGISTIC_REG model type.. BigQuery ML allows users to create and train binary classification models directly on data in BigQuery using SQL, with no need to move data or have deep ML expertise. The LOGISTIC_REG model type implements logistic regression, a standard algorithm for binary classification, and the CREATE MODEL statement handles all the underlying training infrastructure, making it ideal for a data analyst with limited ML skills.

Answer

Use Cloud Datalab to train an XGBoost model on BigQuery data.

Answer

Train a model using Vertex AI Workbench with a custom container.

Answer

Export the data to Cloud Storage and use Vertex AI AutoML Tables.

Question 11

A data science team has deployed a model on Vertex AI and wants to automatically detect when the distribution of a specific feature shifts significantly from the training data. Which service should they use?

Accepted Answer

Vertex AI Model Monitoring. Vertex AI Model Monitoring is the correct service because it is specifically designed to detect feature distribution drift (skew) between training and serving data for deployed models. It continuously monitors the input features and alerts when statistical metrics like the Jensen-Shannon divergence or the L-infinity distance exceed a configured threshold, enabling proactive model retraining.

Answer

Cloud Data Loss Prevention

Answer

Vertex AI Explainable AI

Answer

Cloud Composer

Question 12

A company uses Vertex AI for online predictions with a large ensemble model that requires GPU acceleration. They want to reduce inference latency by batching multiple requests into a single GPU inference call. What should they configure?

Accepted Answer

Deploy the model with NVIDIA Triton Inference Server configured for dynamic batching.. NVIDIA Triton Inference Server supports dynamic batching, which automatically groups multiple inference requests into a single GPU call. This reduces overhead and improves GPU utilization, directly addressing the need to lower latency for online predictions with a large ensemble model on Vertex AI.

Answer

Use Vertex AI Model Optimization for automatic compilation.

Answer

Increase the number of GPU replicas to handle higher concurrency.

Answer

Enable model quantization using TensorRT.

Question 13

A machine learning team is deploying a model for real-time predictions using Vertex AI. They need to ensure that the deployment follows best practices for collaboration and governance. Which TWO actions should they take?

Accepted Answer

Use a continuous integration/continuous deployment (CI/CD) pipeline to deploy model versions.. Using a CI/CD pipeline for deploying model versions ensures automated, repeatable, and auditable deployments, which is a best practice for collaboration and governance. This approach enforces version control, testing, and approval gates, reducing the risk of errors and enabling rollback if needed.

Answer

Store all model artifacts in a local file system to reduce latency.

Answer

Manually configure autoscaling parameters for the endpoint.

Answer

Allow any team member to deploy directly to production without review.

Question 14

A company uses Vertex AI Pipelines with Kubeflow DSL for hyperparameter tuning. They notice that some trials fail due to OOM errors. How should they configure the pipeline to automatically handle this?

Accepted Answer

Add a retry policy to the hyperparameter tuning step with backoff. Vertex AI Pipelines supports retry policies on individual pipeline steps, including hyperparameter tuning jobs. By adding a retry policy with exponential backoff, the pipeline can automatically re-run failed trials caused by transient OOM errors without manual intervention, while avoiding immediate retries that could overload resources.

Answer

Use a larger machine type for the whole pipeline

Answer

Use Cloud Composer to catch failures and resubmit

Answer

Reduce the number of trials

Answer

Increase the memory for all trials in the pipeline definition

Question 15

Your team manages a production ML pipeline on Google Cloud that trains a fraud detection model every 6 hours using new transaction data. The pipeline steps are: (1) Cloud Function triggered by new files in Cloud Storage to validate data, (2) Dataflow job for feature engineering, (3) Vertex AI CustomJob for training, (4) Cloud Function to deploy the model to a Vertex AI endpoint after evaluation. You notice that the pipeline sometimes fails during the Dataflow job step with an error: 'Workflow failed. Causes: The job encountered a system error. Please try again later.' The error occurs sporadically, and retrying the pipeline manually usually succeeds. The team needs a reliable automated solution. What should you do?

Accepted Answer

Orchestrate the pipeline using Cloud Composer with retry policies on the Dataflow operator.. Cloud Composer (Apache Airflow) provides native retry policies on its Dataflow operators, enabling automatic retries of the Dataflow job when it fails due to transient system errors. This addresses the sporadic failure pattern without manual intervention, ensuring the pipeline runs reliably every 6 hours.

Answer

Schedule the pipeline to run less frequently to reduce load on the Dataflow service.

Answer

Use Cloud Tasks to queue the Dataflow job and retry on failure.

Answer

Increase the number of Dataflow workers and use flexRS to handle transient errors.

Question 16

A model serving team notices that during a flash sale, a real-time recommendation model experiences sudden spikes in traffic, causing some requests to time out. The endpoint is configured with `min_replica_count=3`, `max_replica_count=10`, and autoscaling metric set to `target_utilization=0.6` on CPU. Despite this, autoscaling is too slow. What change will most improve the autoscaling responsiveness?

Accepted Answer

Change the autoscaling metric to 'average request count per replica' with an appropriate target.. Using 'average request count per replica' directly measures the load on the endpoint, enabling faster autoscaling response to traffic spikes compared to CPU utilization. Option A is wrong because GPU utilization is not relevant unless the model uses GPU, which is not specified. Option B is wrong because increasing target CPU utilization makes scaling slower, not faster. Option C is wrong because reducing min_replica_count could lead to underprovisioning and does not improve autoscaling responsiveness.

Answer

Add a custom metric based on GPU utilization, assuming the model uses GPU.

Answer

Increase the target CPU utilization to 0.8 to reduce the number of replicas and save cost.

Answer

Reduce `min_replica_count` to 1 to allow more aggressive scaling.

Question 17

A model serving team is experiencing high latency in production. Which TWO actions should they take to diagnose the root cause? (Choose 2.)

Accepted Answer

Enable Cloud Trace to analyze request latency across services.. The correct actions to diagnose root cause of high latency are enabling Cloud Trace (B) and checking autoscaling metrics and cold start frequency (C). Cloud Trace provides detailed latency breakdown across services, helping identify bottlenecks. Checking autoscaling and cold start metrics reveals if latency is due to scaling delays or initialization overhead. Option A (converting framework) is not a diagnostic step and may introduce risk. Option D (increasing replicas) may temporarily reduce load but does not diagnose the cause. Option E (DEBUG logging) adds overhead without providing latency analysis.

Answer

Convert the model to a different framework that is faster.

Answer

Increase the number of replicas to reduce load per replica.

Answer

Set the logging verbosity to DEBUG in the container.

Question 18

Which THREE factors are critical when designing a model serving architecture for a global user base with strict latency SLAs? (Choose 3.)

Accepted Answer

Enable autoscaling with request-based metrics to handle traffic spikes.. Options C, D, and E are correct. Option A is wrong because batch prediction is designed for offline processing of large volumes, not for real-time serving with strict latency SLAs. Option B is wrong because a single-region deployment cannot provide low latency to a global user base and does not address data sovereignty issues appropriately; multi-region deployment with fine-grained controls is needed. Option C is correct: autoscaling with request-based metrics ensures that resources scale dynamically to handle traffic spikes while maintaining latency. Option D is correct: caching idempotent predictions reduces latency for repeated queries and offloads the model server. Option E is correct: multi-region deployment with Vertex AI Endpoints in multiple locations minimizes network distance and latency for users worldwide.

Answer

Use batch prediction to process requests in bulk for efficiency.

Answer

Deploy the model in a single region to avoid data sovereignty issues.

Question 19

A company needs to serve a model for real-time predictions with a strict latency SLA of 100ms at the 99th percentile. The model is lightweight and traffic patterns are highly variable with occasional spikes. Which deployment strategy best meets the SLA while controlling cost?

Accepted Answer

Deploy to Vertex AI Endpoint with min_replica_count=3 and autoscaling enabled.. Setting a minimum number of replicas ensures baseline capacity to handle initial spikes without cold start delays, while autoscaling handles larger spikes. Option A is wrong because Cloud Run with autoscaling to zero may cause cold start delays, which could violate the strict latency SLA. Option B is wrong because manual scaling with a fixed number of replicas may lead to over-provisioning or under-provisioning. Option C is wrong because batch prediction is not real-time.

Answer

Deploy the model as a Cloud Run service with autoscaling to zero.

Answer

Deploy to Vertex AI Endpoint with manual scaling and a fixed number of replicas.

Answer

Use Vertex AI Batch Prediction.

Question 20

A company deploys a model to Vertex AI Endpoint with autoscaling enabled. During a traffic spike, they observe high tail latency (99th percentile > 2s). Which TWO factors are most likely contributing to this latency?

Accepted Answer

The min_replica_count is set too low, causing cold starts.. Options D and E are correct. Option D: if min_replica_count is set too low, during a traffic spike new replicas must be created, and loading the model causes cold start latency, increasing tail latency. Option E: a large model file (e.g., 2GB) increases the time for new replicas to load the model, exacerbating cold start delays. Option A (underpowered machine) would cause higher average latency, not specifically tail latency. Option B (target_cpu_utilization set too low) would cause scaling to occur earlier, potentially reducing tail latency, not contributing to it. Option C (too many traffic splits) is unrelated to tail latency.

Answer

The machine type is underpowered for the model.

Answer

The autoscaling target_cpu_utilization is set too low (e.g., 0.3).

Answer

The endpoint has too many traffic splits configured.