Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Generative AI Leader practice bank has 2,191 more like it. Try 10 free: instant score, no account.
A financial services firm is preparing to deploy a generative AI assistant on Google Cloud to support representatives handling live customer inquiries. During the infrastructure readiness assessment, the architecture team must determine which technical constraints will dictate their model selection, resource provisioning, and deployment topology.
The deployment must satisfy three core conditions:
Which set of technical constraints and architectural factors directly governs these decisions on Google Cloud?
This option describes low-level physical data center facility management and manual hypervisor operations typically associated with traditional on-premises private data centers.
Google Cloud Compute Engine handles host maintenance events transparently via automated live migration, ensuring guest instances stay online without manual scheduling.
This option refers to low-level system administration, custom OS kernel development, and legacy firmware configuration tasks.
Managed infrastructure on Google Cloud automatically receives software patches and updates, allowing architects to focus on workload performance indicators like availability, latency, and throughput.
This option focuses on client-side endpoint hardware and local branch office networking characteristics rather than cloud infrastructure readiness and model hosting parameters.
Cloud-hosted generative AI models process inferences in remote cloud datacenters; infrastructure readiness assessments must focus on cloud compute capacity, network latency between the user and region, and backend processing scale.
When designing and deploying a generative AI solution on Google Cloud, organizations must assess key operational and technical constraints. Evaluating latency targets, computational costs, and infrastructure topology ensures the chosen foundational or fine-tuned model delivers the required performance within budgetary and reliability bounds.

This holistic evaluation directly addresses the trade-offs between model parameter scale, latency overhead, compute expenses, and high-availability design, ensuring a robust production deployment on Google Cloud.
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