Google Professional Machine Learning Engineer
Unlimited Google Professional ML Engineer practice exam retakes, each drawn fresh from a question pool weighted by the official exam domains — 360 questions covering architecting low-code AI, collaborating across teams, scaling prototypes, serving and scaling models, automating ML pipelines, and monitoring AI solutions.
Exam mode Default
120-minute timer, flag for review and a review screen before you submit — just like test day.
Practice mode
See the correct answer, the exam domain and a full explanation after every question.
What you get
- A 305-question pool — every attempt draws 60 fresh questions weighted by the official exam domains
- Unlimited retakes, lifetime access
- Score report by exam domain, with your score trend over time
- Answer review with explanations and reference links
- Original, blueprint-aligned questions — never exam dumps
Ready to sit the real PROFESSIONAL-ML-ENGINEER exam?
Get the official exam voucher and this practice exam is included free (worth US$20.00).
Exam domains
Every attempt draws questions in these official proportions. Open a domain to see the subtopics it covers.
Architecting low-code AI solutions13%
- Building models in BigQuery ML or AutoML based on the business problem
- Performing feature engineering and generating predictions using BigQuery ML
- Training models using Agent Platform AutoML
- Fine-tuning Gemini models using BigQuery
- Evaluating and selecting the appropriate model from Model Garden
- Building applications using industry-specific APIs (Document AI, Vision, Translate)
- Optimizing Gemini-based applications for cost, latency and availability
Collaborating within and across teams to manage data and models16%
- Exploring and preprocessing data for ML
- Model prototyping using notebooks (Agent Platform Workbench, Colab Enterprise)
- Tracking and running ML experiments
Scaling prototypes into ML models20%
- Building models considering cost, complexity, latency and scalability
- Training models
- Choosing appropriate hardware for training
Serving and scaling models20%
- Deploying models for batch and online inference
- Packaging and serving models using prebuilt and custom containers
- Organizing and versioning models in Model Registry
- Implementing model rollout strategies (e.g., A/B testing, canary deployments)
- Managing and serving features using Agent Platform Feature Store
- Deploying models to public and private endpoints
- Scaling the serving backend based on throughput
- Tuning ML models for training and serving in production
Automating and orchestrating ML pipelines18%
- Validating data and models
- Building and orchestrating pipelines with managed or unmanaged services
- Ensuring consistent data preprocessing between training and serving
- Determining an appropriate retraining policy
- Deploying models in CI/CD/CT pipelines (e.g., Cloud Build)
Monitoring AI solutions13%
- Building secure AI systems that protect against data exfiltration and malicious prompting
- Aligning with responsible AI practices (e.g., monitoring for bias)
- Model explainability on Agent Platform
- Configuring Model Monitoring for continuous evaluation of production models
- Monitoring for training-serving skew, data drift and concept drift
- Monitoring, testing and evaluating gen AI solutions
References
- Official exam page:cloud.google.com
- Official study guide:services.google.com (PDF)
Student reviews
No reviews yet — be the first to share your experience.
Tertiary Exams provides original practice questions for learning. We are not affiliated with Google Cloud, and we do not provide real exam dumps.