Google Cloud Professional ML Engineer

Practice Exam Questions & Study Guide

1

Architecting Low-Code AI Solutions

Build ML models using BigQuery ML, ML APIs, foundational models, and AutoML

Section Overview

1.1: Developing ML Models by Using BigQuery ML

3 Question Sets Available

Explore the practical application of BigQuery ML for solving real-world business problems. Learn to identify the right BigQuery ML model for different tasks, including linear and binary classification, regression, time series analysis, and more. Delve into feature engineering techniques within BigQuery ML to optimize model accuracy.

Focus Areas:
  • Building appropriate BigQuery ML models (classification, regression, time-series, matrix factorization, boosted trees, autoencoders)
  • Feature engineering and selection using BigQuery ML
  • Generating predictions (batch and online) using BigQuery ML
  • Evaluating model performance with metrics like R-squared, precision, recall, and F1-score

1.2: Building AI Solutions by Using ML APIs or Foundational Models

2 Question Sets Available

Build AI-powered applications using pre-trained models and APIs available on Google Cloud. Select appropriate Model Garden APIs for tasks like image classification and language translation. Use industry-specific APIs for specialized tasks and build RAG applications with Vertex AI Agent Builder.

Focus Areas:
  • Building applications using ML APIs (Cloud Vision, Natural Language, Cloud Speech, Translation)
  • Using industry-specific APIs (Document AI, Retail API)
  • Implementing RAG applications with Vertex AI Agent Builder

1.3: Training Models by Using AutoML

Sets Available

Prepare data for use with AutoML in Vertex AI. Organize various data types for optimal model training, manage data within Vertex AI, and apply preprocessing steps. Understand feature selection, data labeling, and responsible AI practices for handling sensitive data.

Focus Areas:
  • Preparing data for AutoML (feature selection, data labeling, Tabular Workflows)
  • Using available data types (tabular, text, speech, images, videos) to train custom models
  • Creating forecasting models using AutoML
  • Configuring and debugging trained models
2

Collaborating to Manage Data and Models

Explore and preprocess data, prototype with Jupyter notebooks, track ML experiments

Section Overview

2.1: Exploring and Preprocessing Organization-Wide Data

Sets Available

This section covers the crucial steps in preparing and managing your data for machine learning tasks on Google Cloud. It describes how to choose the most suitable storage service for different data types and volumes, considering factors like cost and access patterns. This section explores data preprocessing techniques using tools like Dataflow, TFX, and BigQuery, covering essential steps such as data cleaning, transformation, and feature engineering. Finally, the section emphasizes responsible AI practices by highlighting the importance of data privacy and security, particularly when dealing with sensitive information. It also explains anonymization techniques and Google Cloud tools that help ensure compliance with privacy regulations.

Focus Areas:
  • Organizing different types of data (e.g., tabular, text, speech, images, videos) for efficient training
  • Managing datasets in Vertex AI.
  • Data preprocessing (e.g., Dataflow, TensorFlow Extended [TFX], BigQuery).
  • Creating and consolidating features in Vertex AI Feature Store.
  • Privacy implications of data usage and/or collection (e.g., handling sensitive data such as personally identifiable information [PII] and protected health information [PHI]).
  • Ingesting different data sources (e.g., text documents) into Vertex AI for inference.

2.2: Model Prototyping Using Jupyter Notebooks

Coming Soon

2.3: Tracking and Running ML Experiments

Coming Soon
3

Scaling Prototypes into ML Models

Build models, train at scale, choose appropriate hardware

Section Overview

3.1: Building Models

Coming Soon

3.2: Training Models

Coming Soon

3.3: Choosing Appropriate Hardware for Training

Coming Soon
4

Serving and Scaling Models

Deploy models for batch and online inference, scale model serving

Section Overview

Questions coming soon for all subsections

5

Automating and Orchestrating ML Pipelines

Develop end-to-end pipelines, automate retraining, track metadata

Section Overview

Questions coming soon for all subsections

6

Monitoring ML Solutions

Identify risks, monitor performance, test and troubleshoot

Section Overview

Questions coming soon for all subsections