Google Cloud Professional Machine Learning Engineer Practice Exams & Study Guide

Developing ML models by using BigQuery ML including building the appropriate BigQuery ML model (linear and binary classification, regression, time-series, matrix factorization, boosted trees, autoencoders) based on the business problem, feature engineering or selection by using BigQuery ML, generating predictions by using BigQuery ML. Building AI solutions by using ML APIs or foundational models including building applications by using ML APIs from Model Garden, building applications by using industry-specific APIs (Document AI API, Retail API), implementing retrieval augmented generation (RAG) applications by using Vertex AI Agent Builder. Training models by using AutoML including preparing data for AutoML (feature selection, data labeling, Tabular Workflows, AutoML), using available data (tabular, text, speech, images, videos) to train custom models, using AutoML for tabular data, creating forecasting models by using AutoML, configuring and debugging trained models.

Exploring and preprocessing organization-wide data (Cloud Storage, BigQuery, Spanner, Cloud SQL, Apache Spark, Apache Hadoop) including organizing different types of data (tabular, text, speech, images, videos) for efficient training, managing datasets in Vertex AI, data preprocessing (Dataflow, TensorFlow Extended [TFX], BigQuery), creating and consolidating features in Vertex AI Feature Store, privacy implications of data usage and/or collection (handling sensitive data such as personally identifiable information [PII] and protected health information [PHI]), ingesting different data sources (text documents) into Vertex AI for inference. Model prototyping using Jupyter notebooks including choosing the appropriate Jupyter backend on Google Cloud (Vertex AI Workbench, Colab Enterprise, notebooks on Dataproc), applying security best practices in Vertex AI Workbench, using Spark kernels, integrating code source repositories, developing models in Vertex AI Workbench by using common frameworks (TensorFlow, PyTorch, sklearn, Spark, JAX), leveraging a variety of foundational and open-source models in Model Garden. Tracking and running ML experiments including choosing the appropriate Google Cloud environment for development and experimentation (Vertex AI Experiments, Kubeflow Pipelines, Vertex AI TensorBoard with TensorFlow and PyTorch) given the framework, evaluating generative AI solutions.

Building models including choosing ML framework and model architecture, modeling techniques given interpretability requirements. Training models including organizing training data (tabular, text, speech, images, videos) on Google Cloud (Cloud Storage, BigQuery), ingestion of various file types (CSV, JSON, images, Hadoop, databases) in training, training using different SDKs (Vertex AI custom training, Kubeflow on Google Kubernetes Engine, AutoML, tabular workflow), using distributed training to organize reliable pipelines, hyperparameter tuning, troubleshooting ML model training failures, fine-tuning foundational models (Vertex AI, Model Garden). Choosing appropriate hardware for training including evaluation of compute and accelerator options (CPU, GPU, TPU, edge devices), distributed training with TPUs and GPUs (Reduction Server on Vertex AI, Horovod).

Serving models including batch and online inference (Vertex AI, Dataflow, BigQuery ML, Dataproc), using different frameworks (PyTorch, XGBoost) to serve models, organizing a model registry, A/B testing different versions of a model. Scaling online model serving including Vertex AI Feature Store, Vertex AI public and private endpoints, choosing appropriate hardware (CPU, GPU, TPU, edge), scaling the serving backend based on throughput (Vertex AI Prediction, containerized serving), tuning ML models for training and serving in production (simplification techniques, optimizing the ML solution for increased performance, latency, memory, throughput).

Developing end-to-end ML pipelines including data and model validation, ensuring consistent data pre-processing between training and serving, hosting third-party pipelines on Google Cloud (MLFlow), identifying components, parameters, triggers, and compute needs (Cloud Build, Cloud Run), orchestration framework (Kubeflow Pipelines, Vertex AI Pipelines, Cloud Composer), hybrid or multicloud strategies, system design with TFX components or Kubeflow DSL (Dataflow). Automating model retraining including determining an appropriate retraining policy, continuous integration and continuous delivery (CI/CD) model deployment (Cloud Build, Jenkins). Tracking and auditing metadata including tracking and comparing model artifacts and versions (Vertex AI Experiments, Vertex ML Metadata), hooking into model and dataset versioning, model and data lineage.

Identifying risks to AI solutions including building secure AI systems by protecting against unintentional exploitation of data or models (hacking), aligning with Google's Responsible AI practices (monitoring for bias), assessing AI solution readiness (fairness, bias), model explainability on Vertex AI (Vertex AI Prediction). Monitoring, testing, and troubleshooting AI solutions including establishing continuous evaluation metrics (Vertex AI Model Monitoring, Explainable AI), monitoring for training-serving skew, monitoring for feature attribution drift, monitoring model performance against baselines, simpler models, and across the time dimension, monitoring for common training and serving errors.