Home Certifications Editorials

Exam overview and study plan

Professional Machine Learning Engineer Practice Questions

Professional Machine Learning Engineer

Read questions, check verified answers and discuss the reasoning. Use reading options to shape your revision, or switch to the simulator for timed practice.

View 45 free questions

45 questions in this view

Page 1 of 8

Question 1

You are optimizing the training of a 175-billion parameter LLM on Gemini Enterprise Agent Platform. You have provisioned a TPU v5p Pod slice with 32 chips for the job. You initially ran the training using standard data parallelism, but the job immediately failed with an out-of-memory (OOM) error. You need to implement a training strategy that resolves the memory issue and minimizes training latency. What should you do?

Configure the training to shard the model parameters and optimizer states, and continue using the data parallelism strategy.
Enable gradient checkpointing, and continue using the data parallelism strategy.
Scale up the TPU Pod slice to include more chips, and continue using the data parallelism strategy.
Configure the training to use a parameter server architecture where the model weights are stored in the host CPU memory.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Question 2

You are building an ML workflow that preprocesses data, trains a model with hyperparameter tuning, and deploys the best model to an Agent Platform endpoint. Your preprocessing step takes two hours and outputs a 100 GB dataset. You run experiments daily with different model architectures using the same preprocessing step. You need to automate this process and optimize the pipeline runs to minimize cost and time. What should you do?

Configure an Agent Platform Pipelines workflow with a single component for the preprocessing and training steps. Use Agent Platform hyperparameter tuning jobs within the component to identify optimal parameters.
Configure an Agent Platform Pipelines workflow with separate components for the preprocessing and training steps. Enable caching on the preprocessing component, and use Agent Platform Serverless Training custom jobs for the training steps.
Configure an Agent Platform Pipelines workflow with separate components for the preprocessing and training steps. Use a Cloud Run function to trigger the pipeline, and configure Agent Platform Serverless Training custom jobs for the training steps.
Configure an Agent Platform Pipelines workflow that starts with an Agent Platform Serverless Training custom job for the preprocessing step. Use a Cloud Run function to launch the hyperparameter tuning job that is triggered when the preprocessed data arrives in Cloud Storage.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Question 3

You deployed a conversational application that uses Gemini. You recently collected thousands of rows of user feedback about the verbosity and accuracy of the model's responses. The feedback indicated that the responses are factually correct but users want different levels of verbosity depending on the type of question. You need to adjust the model to return responses that are more consistent with users' expectations. You want to use a scalable solution and minimize application maintenance. What should you do?

Ask users to indicate all scenarios where they expect concise responses versus verbose responses. Modify the application's prompt to include these scenarios and their respective verbosity levels. Re-evaluate the verbosity of responses with updated prompts.
Ask users to provide examples of responses with the appropriate verbosity as a list of question and answer pairs. Use this dataset to perform supervised fine-tuning (SFT) in Agent Platform. Re-evaluate the verbosity of responses with the tuned version.
Experiment with other models in Model Garden. Perform A/B testing by setting each model as your application's default model. Choose a model based on the results.
Implement a keyword-based routing layer. If the user's input contains the words "detailed" or "description," return a verbose response. If the user's input contains the word "fact," re-prompt Gemini to summarize the response and return a concise response.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Question 4

You have a high-traffic ecommerce application that uses a recommendation model deployed on an Agent Platform endpoint. During flash sales, traffic quickly spikes from 1,000 to 50,000 queries per second (QPS). During these spikes, the application returns 503: Service Unavailable errors because the autoscaler cannot provision new resources quickly enough to meet the sudden demand. Your need to eliminate service disruptions during the start of the sale. How should you configure the endpoint?

Set the min_replica_count to 1 and the max_replica_count to 100 in the deployed model's automatic scaling configuration.
Change the machine type to an a2-highgpu-1g instance with an NVIDIA A100 GPU.
Increase the min_replica_count to a baseline that covers a significant portion of the expected spike, and set the max_replica_count to 100.
Deploy the model to a private Agent Platform endpoint, and autoscale based on GPU utilization.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Question 5

You work for an international bank. Your team is developing a generative AI application that summarizes complex financial reports. You need to implement an automated, scalable solution to evaluate and quantify the quality of generated summaries against the previous version of the solution. What should you do?

Run an automatic side-by-side (AutoSxS) evaluation job in Agent Platform to compare outputs from the new and previous versions of the solution.
Deploy both versions of the solution, and use A/B testing to route a portion of production traffic to the new version and route the remaining traffic to the previous version. Compare user click-through rates.
Use Model Monitoring to track the prediction drift of the token output length.
Run an evaluation job in Agent Platform, and calculate a BLEU score to compare the new and previous versions of the solution.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Question 6

You work for a retail company. You have a managed tabular dataset in Gemini Enterprise Agent Platform that contains regional sales data for each item across stores. The dataset includes several features, such as store name, items sold, and sale timestamp. You want to use the data to train a classification model that predicts whether an item will sell out in each store in the coming week. You need to split the data between the training, validation, and test sets. What approach should you use to split the data?

Use the default data split settings.
Randomly split the data, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set.
Manually split the data, using the store name feature to assign stores to each set.
Chronologically split the data and specify the sales timestamp feature as the time variable.

Select an answer above, then submit your vote. Reading or practicing does not cast a vote.

Page 1 of 8

Build confidence for exam day with expert-reviewed questions and realistic practice. Your next certification starts here.

Company

About Contact Our Authors FAQ

Trust and policies

Methodology Editorial policy Terms and conditions Privacy policy

Contact

ExamPrepare LLC5203 Juan Tabo Blvd STE 2BAlbuquerque, NM 87111[email protected]

© 2026 ExamPrepare LLC. All rights reserved. All certification names, exam codes and logos are the property of their respective owners. All associated trademark and copyright rights belong to those owners. ExamPrepare is not affiliated with, endorsed by, or sponsored by any certification vendor.