support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
CrowdStrike
Anthropic
All Vendors
  1. Home
  2. Exams
  3. Google
  4. PROFESSIONAL MACHINE LEARNING ENGINEER

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps
Professional Machine Learning Engineer Questions 156–160 (page: 33)

Updated On: 25-Oct-2026
Page 33 of 82
PDF with 402 Questions

You work at a healthcare company with strict security policies. Your Google Cloud organization uses a Virtual Private Cloud (VPC) Service Control perimeter to mitigate data exfiltration from Gemini Enterprise Agent Platform. You are creating a training pipeline using Agent Platform Pipelines with the Kubeflow Pipelines (KFP) SDK. During execution, the pipeline fails on a step that installs a public package using the pip install command. You need to resolve this failure while adhering to security policies and best practices.
What should you do?

  1. Add the public package in the packages_to_install parameter in the pipeline component decorator to pull from the PyPI repository.
  2. Increase the job's network timeout setting within the pipeline component configuration.
  3. Create a requirements.txt file with the necessary packages, and upload the text file to a Cloud Storage bucket within the VPC Service Control perimeter. Configure the pipeline step to run the pip install -r command on that file.
  4. Build a custom container image with all required libraries pre-installed, and push the container image to Artifact Registry.

Answer(s): D

Explanation:

A VPC Service Controls perimeter blocks access to public internet services such as the public PyPI repository. Building a custom container image with all required dependencies pre-installed eliminates runtime package downloads. Storing the image in Artifact Registry keeps the required artifacts within Google Cloud and is the recommended production approach for secure pipeline components operating inside a service perimeter.


Reference:

https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/general/vpc-service-controls https://docs.cloud.google.com/artifact-registry/docs/securing-with-vpc-sc



You are developing a machine learning pipeline using the Kubeflow Pipelines (KFP) SDK that will run on Agent Platform Pipelines. The pipeline includes a preprocessing component that takes two hours to transform a large dataset.
You are currently iterating on the code for the subsequent model_training component and need to re-submit the pipeline frequently for testing. You need to ensure that the preprocessing component only re-runs if its inputs or parameters have changed. You want to minimize effort, costs, and total execution time.
What should you do?

  1. Ensure that execution caching is enabled for the preprocessing component by including the set_caching_options(enable_caching=True) method.
  2. Track the run lineage using Agent Platform Experiments, and pass the output artifact URI from the previous run into the training component.
  3. Configure the pipeline to write the preprocessed data to a persistent volume claim (PVC) that is shared across pipeline runs.
  4. Add a dsl.Condition step to the pipeline that checks if the preprocessing step has executed in the last hour.

Answer(s): A

Explanation:

Execution caching reuses the preprocessing component’s previous successful output when its inputs, parameters, and component definition have not changed. This prevents the two-hour transformation from running during repeated pipeline tests, reducing both execution time and compute cost.



Your data science team needs to rapidly experiment with various features, model architectures, and hyperparameters. They need to track the accuracy metrics for various experiments and use an API to query the metrics over time.
What should they use to track and report their experiments while minimizing manual effort?

  1. Use Vertex Al Pipelines to execute the experiments. Query the results stored in MetadataStore using the Vertex AI API.
  2. Use Vertex AI Training to execute the experiments. Write the accuracy metrics to BigQuery, and query the results using the BigQuery API.
  3. Use Vertex AI Training to execute the experiments. Write the accuracy metrics to Cloud Monitoring, and query the results using the Monitoring API.
  4. Use Vertex AI Workbench user-managed notebooks to execute the experiments. Collect the results in a shared Google Sheets file, and query the results using the Google Sheets API.

Answer(s): A



You are creating a retraining policy for a customer churn prediction model deployed in Vertex AI. New training data is added weekly. You want to implement a model retraining process that minimizes cost and effort.
What should you do?

  1. Retrain the model when a significant shift in the distribution of customer attributes is detected in the production data compared to the training data.
  2. Retrain the model when the model's latency increases by 10% due to increased traffic.
  3. Retrain the model when the model accuracy drops by 10% on the new training dataset.
  4. Retrain the model every week when new training data is available.

Answer(s): A

Explanation:

Retraining based on detected significant data distribution shifts ensures the model stays relevant and accurate while minimizing unnecessary retraining costs and effort. This approach is more efficient than retraining on a fixed schedule or solely based on accuracy metrics.



You work for a large social network service provider whose users post articles and discuss news. Millions of comments are posted online each day, and more than 200 human moderators constantly review comments and flag those that are inappropriate. Your team is building an ML model to help human moderators check content on the platform. The model scores each comment and flags suspicious comments to be reviewed by a human.
Which metric(s) should you use to monitor the model’s performance?

  1. Number of messages flagged by the model per minute
  2. Number of messages flagged by the model per minute confirmed as being inappropriate by humans.
  3. Precision and recall estimates based on a random sample of 0.1% of raw messages each minute sent to a human for review
  4. Precision and recall estimates based on a sample of messages flagged by the model as potentially inappropriate each minute

Answer(s): D



  PDF
Viewing page 33 of 82
Viewing questions 161 - 165 out of 402 questions


Post your Comments and Discuss Google PROFESSIONAL MACHINE LEARNING ENGINEER exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!