Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Professional Cloud Architect practice bank has 2,335 more like it. Try 10 free: instant score, no account.
An enterprise is designing a deployment workflow to integrate an open-source machine learning model discovered in Vertex AI Model Garden into an existing cloud-native application. The architecture must satisfy several key operational requirements:
Which deployment and integration strategy should you recommend?
This option attempts to host the model container as a serverless web service using Cloud Run, placing it behind an external Application Load Balancer with Cloud CDN caching, while granting broad BigQuery privileges to the client service account.
You were hosting a lightweight microservice or static web application that serves cached assets and performs data warehousing administration in BigQuery.
This configuration downloads model binaries onto standalone Compute Engine virtual machines running as Spot VMs inside an unmanaged instance group, relying on static API keys in client request headers for authentication.
The workload were an asynchronous, low-cost batch processing job that could tolerate sudden node preemption and retries.
This architecture creates a model definition inside BigQuery ML and uses a scheduled SQL query execution pipeline every minute to process inference requests, while assigning administrative permissions for Vertex AI Feature Store.
roles/aiplatform.featurestoreAdmin) role grants broad configuration rights over feature management rather than the least-privilege roles/aiplatform.user role needed to invoke model predictions.The goal was to run offline analytical batch scoring jobs once an hour or daily on large structured data tables directly within BigQuery.
This architecture leverages Google Cloud's native CI/CD and MLOps toolset to manage the deployment lifecycle of Vertex AI Model Garden assets. It combines Cloud Build for automated packaging and testing with Cloud Deploy for controlled delivery to Vertex AI endpoints, while securing model access using IAM roles.
roles/aiplatform.user) role to the client application's dedicated service account satisfies the principle of least privilege, enabling secure token-based authentication to invoke online predictions without exposing credentials.
This approach aligns with Google Cloud architecture best practices for operational excellence in machine learning. It avoids manual operational overhead and fragmented infrastructure while delivering an enterprise-grade serving environment tailored for foundation and open-source models.
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated