Question 1

As a Gen AI engineer, you are preparing to deploy a large application that integrates multiple LLMs and external GenAI services. What is a critical step to ensure the deployment is successful and the application runs smoothly in production?

Options :

A : Prioritize optimizing each model-s performance before deployment to maximize efficiency.

B : Concentrate on reducing the overall application size to ensure faster deployment and lower resource usage.

C : Package the entire application together, including all models, endpoints, and necessary configurations, to ensure that all components function cohesively as part of a unified deployment pipeline.

D : Focus on deploying each LLM model separately to ensure flexibility and modular updates.

Answer: C

Question 2

As a Gen AI engineer, you're tasked with setting up a system to store and manage embeddings for a search application. To ensure that your embedding index stays up-to-date as new data is added, which configuration should you enable when saving embeddings to a Delta table?

Options :

A : Enable Delta Table Versioning

B : Enable Delta Cache for faster queries

C : Enable Change Data Feed

D : Enable Delta Lake optimization

Answer: C

Question 3

As a Gen AI engineer, you’re tasked with monitoring your AI system to ensure it performs effectively and cost-efficiently. Which of the following scenarios best represents an effective monitoring strategy for diagnosing potential issues in your AI model?

Options :

A : Monitoring the system-s user interface for aesthetic design improvements and user experience enhancements

B : Regularly reviewing input data, prompt queries and responses to identify any inconsistencies or anomalies.

C : Focusing solely on analyzing performance/cost details without reviewing mid-training checkpoints or human feedback.

D : Evaluating the model’s performance only during final deployment phases to ensure it meets all business requirements

Answer: B

Question 4

When choosing between "Deploy Model" and "Deploy Code" patterns in a Databricks environment, which approach is generally recommended for more effective management of ML workflows?

Options :

A : Deploy Model: Move the model artifact from staging to production after training in the dev environment, and handle other code (inference, monitoring) separately.

B : Deploy Code: Develop and test code in separate environments, then deploy it to production, ensuring the training pipeline is also run in each environment while deploying the model only in production.

C : Deploy Model: Train the model in the development environment and deploy it directly to production without separate processes for inference and monitoring.

D : Deploy Code: Train the model only in the production environment and use the same environment for testing and deployment.

Answer: B

Question 5

A Generative Al Engineer is responsible for developing a chatbot to enable their companys internal HelpDesk Call Center team to more quickly find related tickets and provide resolution. While creating the GenAI application work breakdown tasks for this project, they realize they need to start planning which data sources (either Unity Catalog volume or Delta table) they could choose for this application. They have collected several candidate data sources for consideration: call_rep_history: a Delta table with primary keys representative_id, call_id. This table is maintained to calculate representatives call resolution from fields call_duration and call start_time. transcript Volume: a Unity Catalog Volume of all recordings as a *.wav files, but also a text transcript as *.txt files. call_cust_history: a Delta table with primary keys customer_id, cal1_id. This table is maintained to calculate how much internal customers use the HelpDesk to make sure that the charge back model is consistent with actual service use. call_detail: a Delta table that includes a snapshot of all call details updated hourly. It includes root_cause and resolution fields, but those fields may be empty for calls that are still active. maintenance_schedule “ a Delta table that includes a listing of both HelpDesk application outages as well as planned upcoming maintenance downtimes. They need sources that could add context to best identify ticket root cause and resolution. Which TWO sources do that? (Choose two.)

Options :

A : call_cust_history

B : maintenance_schedule

C : call_rep_history

D : call_detail

E : transcript Volume

Answer: D,E

Confidently Practice Online with Free Databricks-Certified-Generative-AI-Engineer-Associate Exam Cram

Buying Options: