nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #288

You work for a large bank that serves customers through an application hosted in Google Cloud that is running in the US and Singapore. You have developed a PyTorch model to classify transactions as…

The correct answer is D. Create another Vertex AI endpoint in the asia-southeast1 region, and allow the application to. By having an endpoint in the asia-southeast1 region (Singapore), the data doesn't have to travel as far, significantly reducing the round-trip time. Allowing the application to choose the appropriate endpoint based on the user's location ensures that requests are handled by the…

Submitted by tom_us· Apr 18, 2026Monitoring, optimizing, and maintaining ML solutions

Question

You work for a large bank that serves customers through an application hosted in Google Cloud that is running in the US and Singapore. You have developed a PyTorch model to classify transactions as potentially fraudulent or not. The model is a three-layer perceptron that uses both numerical and categorical features as input, and hashing happens within the model. You deployed the model to the us-central1 region on nl-highcpu-16 machines, and predictions are served in real time. The model's current median response latency is 40 ms. You want to reduce latency, especially in Singapore, where some customers are experiencing the longest delays. What should you do?

Options

  • AAttach an NVIDIA T4 GPU to the machines being used for online inference.
  • BChange the machines being used for online inference to nl-highcpu-32.
  • CDeploy the model to Vertex AI private endpoints in the us-central1 and asia-southeast1 regions,
  • DCreate another Vertex AI endpoint in the asia-southeast1 region, and allow the application to

How the community answered

(19 responses)
  • A
    5% (1)
  • C
    11% (2)
  • D
    84% (16)

Explanation

By having an endpoint in the asia-southeast1 region (Singapore), the data doesn't have to travel as far, significantly reducing the round-trip time. Allowing the application to choose the appropriate endpoint based on the user's location ensures that requests are handled by the nearest available server, optimizing response times for users in different regions.

Topics

#Latency reduction#Multi-region deployment#Vertex AI Endpoints#Network latency

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice