Google Professional Machine Learning Engineer exam dumps

Google Professional Machine Learning Engineer practice question 333 of 522

Professional Machine Learning Engineer. Professional level, Google Cloud. Free question with the correct answer and a full explanation.

Google Professional Machine Learning Engineer Question 333

Select 2Google Cloud Platform

You are a Machine Learning Engineer responsible for deploying a custom model on Vertex AI. The model will handle sensitive data, and company policy mandates that the traffic should not traverse the public internet. What steps should you take to ensure compliance with the policy while deploying the model on Vertex AI?

  1. A

    Configure the Vertex AI endpoint to use a private endpoint by enabling Private Service Connect.

  2. B

    Ensure the model is deployed in the same region as your VPC network for reduced latency.

  3. C

    Grant the Vertex AI service account the 'Private Service Connect Admin' role.

  4. D

    Enable the Vertex AI public endpoint and use IP whitelisting to restrict access.

  5. E

    Connect your on-premises or other services to Vertex AI using a VPN or Interconnect paired with Private Service Connect.

Show answer and explanation

Correct answers: A, E

Explanation

To comply with the requirement of avoiding public internet traffic, you must use Private Service Connect to set up private endpoints for Vertex AI. Additionally, connecting on-premises or other services to Vertex AI via a VPN or Interconnect ensures secure communication. Public endpoints or IP whitelisting do not meet the compliance requirement as they still involve the public internet.

  • A. Correct.

    Correct: Private Service Connect allows Vertex AI to use private endpoints, ensuring that traffic does not traverse the public internet.

  • B. Incorrect.

    Incorrect: While deploying the model in the same region as your VPC network is a best practice for latency, it does not enforce the use of private endpoints.

  • C. Incorrect.

    Incorrect: Granting the 'Private Service Connect Admin' role is not necessary for using Private Service Connect with Vertex AI. The required roles must simply allow configuration of Private Service Connect.

  • D. Incorrect.

    Incorrect: Enabling public endpoints and relying on IP whitelisting still uses the public internet, which violates the policy requirement.

  • E. Correct.

    Correct: Using a VPN or Interconnect in combination with Private Service Connect ensures secure traffic routing without traversing the public internet.

Timed practice exam

Take a Google Professional Machine Learning Engineer practice test under exam conditions

60 questions in 120 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam

More Google Professional Machine Learning Engineer practice questions

  1. 334.You are tasked with building a machine learning model to process large batches of images for...
  2. 335.You are designing a machine learning pipeline to train a deep learning model on a large image...
  3. 336.You are designing a machine learning pipeline for a deep learning model that involves training on a...
  4. 337.You are designing a machine learning pipeline to train a deep learning model for image...
  5. 338.You are designing a machine learning system for a client that requires low latency for real-time...
Back to the Google Professional Machine Learning Engineer exam dumps