GOOGLE CLOUDGoogle Cloud Professional Machine Learning Engineer
The Google Cloud Professional Machine Learning Engineer certification validates your ability to design, build, and productionize machine learning models to solve business problems. It is for ML engineers and data scientists who architect scalable, reliable, and responsible ML solutions on Google Cloud. Earning it demonstrates you can turn ML experiments into secure, cost-effective, and maintainable production systems.
381 practice questions · Updated 2026-07-30
6Domains
14Objectives
113Concepts
381Questions
PROFESSIONAL-MACHINE-LEARNING-ENGINEER Curriculum
Every domain, objective, and concept the PROFESSIONAL-MACHINE-LEARNING-ENGINEER exam measures.
- Selecting BigQuery ML model types
- Building classification models in BigQuery ML
- Building regression models in BigQuery ML
- Building forecasting models in BigQuery ML
- Building clustering models in BigQuery ML
- Performing feature engineering in BigQuery ML
- Performing feature selection in BigQuery ML
- Generating predictions with BigQuery ML
- Training models with Agent Platform AutoML
- Fine-tuning Gemini models using BigQuery
- Model selection criteria
- Industry-specific AI APIs
- Model tuning and customization
- Cost optimization for Gemini applications
- Latency optimization for Gemini applications
- Availability and reliability for Gemini applications
- Data type exploration strategies
- Tool selection for data preprocessing
- Feature store creation and consolidation
- Data privacy and PII handling
- Notebook environment setup and access control
- Collaborative features and version control in notebooks
- Data security and privacy in notebooks
- Developing models with PyTorch in notebooks
- Developing models with scikit-learn in notebooks
- Developing models with JAX in notebooks
- Exploring and using models from Model Garden
- Integrating Model Garden models into notebook workflows
- Prototyping with Vertex AI and notebook integration
- Choosing Google Cloud environments for ML development
- Using Experiments on Gemini Enterprise Agent Platform
- Using Gemini Enterprise Agent Platform Pipelines
- Using Kubeflow Pipelines
- Evaluating predictive ML models
- Evaluating generative AI solutions
- Using LLM-as-a-judge for evaluation
- Tracking model artifacts and versions
- Comparing model experiments
- Managing model lineage
- Model type selection criteria
- Product selection for ML workflows
- Deployment strategy selection
- Interpretability-aware modeling techniques
- Data organization on Google Cloud
- Data ingestion for training pipelines
- Training with custom SDKs
- Training with AutoML and Tabular Workflows
- Training job organization
- Troubleshooting training failures
- Hyperparameter tuning
- Fine-tuning foundational models
- Evaluate compute options
- Evaluate accelerator options
- Understand data parallelism
- Understand model parallelism
- Choose parallelism strategy
- Batch vs. online inference
- Agent Platform for model serving
- Model Garden deployment
- Cloud Run for model serving
- GKE for model serving
- Prebuilt containers
- Custom containers
- Model Registry organization
- Model versioning
- A/B testing rollout
- Canary deployment
- Inference preprocessing
- Inference postprocessing
- Feature Store fundamentals
- Serving features from Feature Store
- Feature Store configuration and monitoring
- Public and private endpoints
- Deploying models to endpoints
- Endpoint security and access control
- Hardware selection for serving
- Hardware optimization and cost trade-offs
- Scaling serving infrastructure
- Containerized serving and inference platforms
- Throughput and latency management
- Model tuning for production
- Serving-specific model optimization
- Production model lifecycle management
- Data validation
- Model validation
- Pipeline orchestration with managed services
- Pipeline orchestration with unmanaged services
- Using templates for pipelines
- Custom pipeline solutions
- Consistent data preprocessing between training and serving
- Retraining triggers
- Retraining frequency trade-offs
- Retraining policy design
- CI/CD pipeline fundamentals
- Continuous training (CT) pipelines
- Cloud Build for ML pipelines
- Model deployment automation
- Pipeline orchestration
- Monitoring and rollback in pipelines
- Data exfiltration prevention
- Malicious prompting defense
- Sensitive data sharing with LLMs
- Security tools for AI systems
- Responsible AI bias monitoring
- Model explainability on Agent Platform
- Model Monitoring on Gemini Enterprise Agent Platform
- Training-Serving Skew Detection
- Data Drift Monitoring
- Concept Drift Monitoring
- Feature Attribution Drift Monitoring
- Monitoring Gen AI Solutions
- Testing Gen AI Solutions
- Evaluating Gen AI Solutions
Ready to practice?Test your knowledge with exam-style questions or take an intelligent quiz tailored to your level.
Percentages reflect share of the current practice bank, not official exam weightings — no structured per-skill weight is published for PROFESSIONAL-MACHINE-LEARNING-ENGINEER, so none is invented.