support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
CrowdStrike
Anthropic
All Vendors
  1. Home
  2. Exams
  3. Google
  4. PROFESSIONAL MACHINE LEARNING ENGINEER

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps
Professional Machine Learning Engineer Questions 61–65 (page: 14)

Updated On: 25-Oct-2026
Page 14 of 82
PDF with 402 Questions

You work in the credit card fraud detection department of a bank that processes millions of transactions per day. You need to create and serve a real-time fraud detection model. To address the challenge of feature engineering at this scale with limited raw data, you plan to create time-related aggregate features, such as the average transaction amount within the last month or the amount of time since the last transaction. How should you process the data for model training and serving?

  1. Ingest the transaction data into BigQuery. Use the TRANSFORM clause in BigQuery ML to create new features by applying SQL functions to the raw transaction data.
  2. Create streaming Dataflow pipelines that read transaction data from Pub/Sub. Use a windowing function to aggregate transaction data over time. Store the engineered features in Agent Platform Feature Store.
  3. Ingest the transaction data into BigQuery. Use a TRANSFORM_ONLY model in BigQuery ML to create a reusable feature engineering pipeline. Use this pipeline to preprocess the data.
  4. Orchestrate a workflow in Agent Platform Pipelines that exports raw transaction data from BigQuery to Cloud Storage. Perform feature engineering using a Python script in a custom component in the pipeline.

Answer(s): B

Explanation:

A streaming Dataflow pipeline can process millions of transaction events from Pub/Sub and use stateful, windowed aggregations to calculate time-dependent features such as monthly average transaction amounts and time since the previous transaction. Storing these engineered values in Agent Platform Feature Store makes consistent features available for both model training and low-latency online serving.


Reference:

https://docs.cloud.google.com/dataflow/docs/concepts/streaming-pipelines https://docs.cloud.google.com/dataflow/docs/concepts/streaming-with-cloud-pubsub



Your organization’s employee onboarding team wants you to build an interactive self-help tool for new employees. The tool needs to receive queries from users and provide answers from the organization’s internal documentation. This documentation is spread across standalone documents such as PDF files. You want to build a solution quickly while minimizing maintenance overhead.
What should you do?

  1. Create a custom chatbot user interface hosted on App Engine. Use Agent Platform to fine-tune a Gemini model on the organization’s internal documentation. Send users’ queries to the fine-tuned model by using the custom chatbot and return the model’s responses to the users.
  2. Deploy an internal website to a Google Kubernetes Engine (GKE) cluster. Build a search index by ingesting all of the organization’s internal documentation. Use Vector Search to implement a semantic search that retrieves results from the search index based on the query entered into the search box.
  3. Use Agent Search to create an agent. Securely index the organization’s internal documentation to the agent’s datastore. Send users’ queries to the agent and return the agent’s grounded responses to the users.
  4. Deploy an internal website to a Google Kubernetes Engine (GKE) cluster. Organize the relevant internal documentation into sections. Collect user feedback on website content and store it in BigQuery. Request that the onboarding team regularly update the links based on user feedback.

Answer(s): C

Explanation:

Agent Studio is specifically designed for building conversational AI agents quickly with minimal overhead. It allows for secure indexing of internal documents, making them accessible for semantic query resolution. By indexing the internal documentation in the Agent Search data store, the system can provide grounded and accurate responses to user queries based on the organization's documentation. This approach minimizes the maintenance overhead as the Agent Platform handles much of the complexity, including semantic search and conversational interface.



You work at a large organization that recently decided to move their ML and data workloads to Google Cloud. The data engineering team has exported the structured data to a Cloud Storage bucket in Avro format. You need to propose a workflow that performs analytics, creates features, and hosts the features that your ML models use for online prediction. How should you configure the pipeline?

  1. Ingest the Avro files into Cloud Spanner to perform analytics. Use a Dataflow pipeline to create the features, and store them in Vertex AI Feature Store for online prediction.
  2. Ingest the Avro files into BigQuery to perform analytics. Use a Dataflow pipeline to create the features, and store them in Vertex AI Feature Store for online prediction.
  3. Ingest the Avro files into Cloud Spanner to perform analytics. Use a Dataflow pipeline to create the features, and store them in BigQuery for online prediction.
  4. Ingest the Avro files into BigQuery to perform analytics. Use BigQuery SQL to create features and store them in a separate BigQuery table for online prediction.

Answer(s): B



Your company needs to generate product summaries for vendors. You evaluate a foundation model from Model Garden for text summarization and find the style of the summaries are not aligned with your company's brand voice. How should you improve this LLM-based summarization model to better meet your business objectives?

  1. Replace the pre-trained model with another model in Model Garden.
  2. Fine-tune the model using a company-specific dataset.
  3. Increase the model's temperature parameter.
  4. Tune the token output limit in the response.

Answer(s): B

Explanation:

Fine-tuning the foundation model with a company-specific dataset helps align the generated summaries with the desired brand voice and style, tailoring the model’s outputs to meet business objectives effectively.



You manage a custom chum prediction model in Model Registry. Your production application currently submits batch prediction jobs using this model by referencing a custom model alias named production. You have trained a new version of the model that has higher accuracy. You need to ensure that the application uses the new model version for the next batch prediction job without modifying the application code or configuration.
What should you do?

  1. Overwrite the production model's artifact files in Cloud Storage with the new model's artifacts.
  2. Configure a Cloud Build trigger to automatically update the model path in 'the batch prediction job definition.
  3. Move the production model alias from the old model version to the new model version.
  4. Update the Agent Platform endpoint associated with the production model to route 100% of traffic to the new model version.

Answer(s): C

Explanation:

Model aliases provide a stable reference that can be reassigned between model versions. Moving the production alias to the newly trained version allows the next batch prediction job to automatically use that version without changing the application's code or configuration.



  PDF
Viewing page 14 of 82
Viewing questions 66 - 70 out of 402 questions


Post your Comments and Discuss Google PROFESSIONAL MACHINE LEARNING ENGINEER exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!