PMLE Practice Test 39 — 15 Questions

Question 1

You are deploying a pre-trained BERT model for inference on edge devices. The model must be under 500 MB and inference latency under 50 ms. Which approach should you take?

Accepted Answer

Apply post-training INT8 quantization using TensorFlow Lite. Post-training INT8 quantization reduces model size by approximately 75% (from ~440 MB to ~110 MB for BERT-Base) and accelerates inference on edge devices via integer arithmetic, easily meeting the 500 MB and 50 ms constraints. TensorFlow Lite provides hardware-optimized kernels for ARM CPUs and NPUs, making it ideal for edge deployment without requiring retraining.

Answer

Use a larger model like BERT-Large and deploy on GPU

Answer

Prune 50% of the model weights and fine-tune

Answer

Use knowledge distillation to train a smaller student model from scratch

Question 2

An ML engineer is using Vertex AI for distributed training of a PyTorch model across multiple nodes. The training job must use TPUs for high throughput. The engineer sets up the job configuration. Which THREE components are required for the training to work correctly? (Select 3)

Accepted Answer

A startup script to configure the TPU pod (e.g., `xla_lib.sh`). A is correct because TPU pods require a startup script (e.g., `xla_lib.sh`) to initialize the XLA runtime, configure the TPU mesh, and set environment variables like `XRT_TPU_CONFIG`. Without this script, the TPU devices will not be discoverable by the PyTorch/XLA process, causing the training to fail with device-not-found errors.

Answer

A MultiWorkerMirroredStrategy configuration

Answer

A TF_CONFIG environment variable set for each worker

Question 3

An engineer is training a model on Vertex AI using a custom container. The training job fails with an error indicating that the container exited with a non-zero status. The engineer wants to debug the issue. What is the best way to access the logs?

Accepted Answer

Check the logs in Cloud Logging (Logs Explorer). Vertex AI automatically streams all container stdout and stderr to Cloud Logging (Logs Explorer). When a custom container exits with a non-zero status, the detailed error messages, stack traces, and application logs are captured there, making it the primary and most comprehensive debugging tool. Cloud Logging provides structured, searchable logs without requiring direct access to the container.

Answer

SSH into the training container using Vertex AI's SSH feature

Answer

View logs in Cloud Storage under the job's output directory

Answer

Use Cloud Debugger to inspect the container

Question 4

A machine learning model deployed on Vertex AI is returning erroneous predictions. The team needs to investigate the root cause by examining the prediction request and response details. Which Google Cloud tool is best suited for this?

Accepted Answer

Cloud Logging. Cloud Logging is the correct tool because it captures detailed logs of prediction requests and responses, including input features, model outputs, and any errors. By examining these logs, the team can trace the exact data flow and identify discrepancies causing erroneous predictions, such as data preprocessing issues or model version mismatches.

Answer

Cloud Monitoring

Answer

Cloud Debugger

Answer

Cloud Trace

Question 5

A company uses Cloud Composer to orchestrate a nightly ML workflow that includes running a Vertex AI pipeline, querying BigQuery, and running a Dataflow job. The Airflow DAG must run only if the previous day's Dataflow job succeeded. Which Airflow concept should they use to implement this dependency?

Accepted Answer

Use the bitshift operators (>>) to set the execution order: Dataflow_task >> VertexAI_pipeline.. Airflow's bitshift operators (>>) define task dependencies in a DAG. By setting `Dataflow_task >> VertexAI_pipeline`, the Vertex AI pipeline task will only execute after the Dataflow task has completed successfully. This directly enforces the required dependency without additional logic or branching.

Answer

Use a BranchPythonOperator to check the status of the Dataflow job before proceeding.

Answer

Nest the tasks in a SubDAG with a schedule_interval that starts after the expected Dataflow completion time.

Answer

Set a TriggerRule on the Vertex AI pipeline task to 'all_done' and reference the previous task.

Question 6

You need to perform a large-scale feature computation on streaming data from Pub/Sub, transforming raw events into features, and writing results to Vertex AI Feature Store for online serving. Which Google Cloud architecture is most appropriate?

Accepted Answer

Use Dataflow streaming pipeline with Apache Beam to read from Pub/Sub, compute features, and write to Feature Store. Dataflow with streaming (Apache Beam) can read from Pub/Sub, transform data, and write to Feature Store via the online serving API. Cloud Functions is not suitable for complex transforms. Dataproc Streaming is possible but Dataflow is more natural. Cloud Run is for request-response.

Answer

Use Dataproc with Spark Streaming to read from Pub/Sub and write to Feature Store

Answer

Use Cloud Functions triggered by Pub/Sub to compute features and update Feature Store

Answer

Use Cloud Run to consume Pub/Sub messages and update Feature Store via a service

Question 7

Which API is recommended for high-throughput, low-latency online prediction requests to Vertex AI endpoints?

Accepted Answer

gRPC API. gRPC API is recommended for high-throughput, low-latency online prediction requests to Vertex AI endpoints because it uses HTTP/2 for multiplexed streaming, binary serialization (Protocol Buffers), and supports bidirectional streaming, which reduces latency and improves throughput compared to REST. Vertex AI's prediction service natively supports gRPC for real-time inference, making it the optimal choice for latency-sensitive applications.

Answer

Cloud Functions

Answer

REST API

Answer

Cloud Pub/Sub

Question 8

You need to serve a model on an edge device with low latency and offline capability. Which approach should you use?

Accepted Answer

Export the model to TensorFlow Lite and use Vertex AI Edge Manager for deployment.. TensorFlow Lite is specifically designed for on-device inference with low latency and offline capability, converting models into a lightweight format optimized for edge hardware. Vertex AI Edge Manager extends this by providing deployment, monitoring, and management of models on edge devices, ensuring they run efficiently without constant cloud connectivity.

Answer

Use Cloud Run for on-device inference.

Answer

Deploy the model to a Vertex AI endpoint and rely on mobile connectivity.

Answer

Use AI Platform Prediction (not Vertex AI).

Question 9

A data scientist wants to define a lightweight Python function component in Vertex AI Pipelines using Kubeflow Pipelines SDK v2. Which decorator should be applied to the function to make it a pipeline component?

Accepted Answer

@dsl.component. In KFP SDK v2, the @dsl.component decorator is used to define a Python function component. @dsl.pipeline is for defining a pipeline that composes multiple components. The other options are not valid decorators.

Answer

@dsl.pipeline

Answer

@kfp.v2.components.func_to_component

Answer

@kfp.dsl.component

Question 10

An e-commerce company deployed a Vertex AI AutoML Tables model to predict customer churn. The model is served via a private endpoint with a dedicated machine type n1-standard-4. After a week, they observe that 5% of predictions fail with 'Request timed out' error. The average prediction time is 1.2 seconds but spikes to 4 seconds during peak hours. The input data is 50 features. They have enabled autoscaling with a min node count of 1 and max of 5. Which action is most likely to resolve the timeout issue without increasing complexity?

Accepted Answer

Increase the max node count to 10.. The timeout errors during peak hours indicate that the single endpoint instance is overwhelmed. Increasing the max node count from 5 to 10 allows autoscaling to spin up more replicas during traffic spikes, distributing the load and reducing latency. Option A (reducing features) would require retraining and could degrade model accuracy. Option C (model monitoring) detects data drift but does not address compute capacity. Option D (increasing memory) may help if the model is memory-bound, but n1-standard-4 already has 15 GB RAM; timeout errors are more likely due to CPU saturation, not memory exhaustion.

Answer

Reduce the number of features to 30.

Answer

Enable model monitoring to detect data drift.

Answer

Change the machine type to n1-highmem-4 to increase memory.

Question 11

An e-commerce company uses a recommendation model deployed on Vertex AI Endpoints. The model's latency increases gradually over two weeks, causing timeouts. The model is served using a custom container. What is the most likely root cause and corrective action?

Accepted Answer

The custom container has a memory leak; implement memory monitoring and set container resource limits.. A gradual increase in latency over two weeks, without a sudden spike, strongly indicates a memory leak in the custom container. As the leak accumulates, the container's garbage collection becomes less effective, leading to increased GC pauses and eventual timeouts. Setting resource limits and monitoring memory usage can prevent the container from exhausting host memory and causing performance degradation.

Answer

The model is receiving more traffic; scale the number of replicas.

Answer

The Vertex AI endpoint has changed its URL; update the client application.

Answer

The model file size has grown due to feature engineering; reduce feature count.

Question 12

A company needs to extract key fields from scanned invoices, such as invoice number and total amount, with high accuracy. They want a managed service and plan to use human review for low-confidence results. Which combination of services should they use?

Accepted Answer

Document AI and Human-in-the-Loop. Document AI provides specialized processors like invoice parser, and Human-in-the-Loop (HITL) can be integrated for low-confidence predictions. Vision API is generic OCR, Natural Language API is for text analysis, and Translation API is for language translation.

Answer

Vision API and Natural Language API

Answer

Translation API and AutoML Vision

Answer

BigQuery ML and Vertex AI Prediction

Question 13

A data engineer wants to orchestrate a complex workflow that includes running a Vertex AI pipeline, then a BigQuery job, and finally a Dataflow pipeline. The workflow must handle dependencies, retries, and monitoring. Which Google Cloud service is most suitable for this orchestration?

Accepted Answer

Cloud Composer. Cloud Composer (based on Apache Airflow) is the most suitable service for orchestrating a complex workflow with dependencies, retries, and monitoring across Vertex AI, BigQuery, and Dataflow. It provides a managed Airflow environment that natively supports DAG-based orchestration, built-in retry logic, and integration with Google Cloud services via operators like VertexAIPipelineOperator, BigQueryOperator, and DataflowTemplatedJobStartOperator.

Answer

Cloud Tasks

Answer

Cloud Scheduler

Answer

Workflows

Question 14

Your team has deployed a scikit-learn model using a custom container on Vertex AI Prediction. The model receives about 100 requests per second, and the endpoint is configured with a single n1-standard-4 machine. You notice that response times are around 200 ms on average, but occasionally spike to over 10 seconds during traffic bursts. You have set the min replicas to 1 and max replicas to 10. Despite this, spikes still occur. What is the most likely cause and the best course of action?

Accepted Answer

The autoscaling is too slow to react; you should increase the max replicas to 20 and reduce the cooldown period.. The occasional spikes during traffic bursts indicate that the autoscaling is not reacting quickly enough. Increasing max replicas to 20 allows more room to scale, and reducing the cooldown period makes the autoscaler add replicas faster when load increases. This addresses the immediate spikes.

Answer

The model is not optimized for parallel inference; you should enable batching in the custom container.

Answer

The machine type is insufficient for the model size; you should switch to a n1-highmem-8.

Answer

The container has a memory leak; you should restart the container periodically.

Question 15

A team uses Vertex AI Explainable AI with integrated gradients for a deep learning model. They want to reduce the computational cost of explanations without significantly reducing explanation quality. Which configuration change should they make?

Accepted Answer

Reduce the number of integral approximation steps.. Integrated gradients approximates Shapley values by integrating gradients along a path. Reducing the number of steps (integral approximation steps) reduces computation, but may reduce quality. A moderate reduction balances cost and quality.

Answer

Switch from integrated gradients to XRAI.

Answer

Apply feature attribution to only a random subset of predictions.

Answer

Use sampled Shapley instead, as it is always cheaper.