Skip to main content

Data Engineering with Databricks

This is an introductory course that serves as an appropriate entry point to learn Data Engineering with Databricks. 

Below, we describe each of the four, four-hour modules included in this course.


Note: For the following four modules, the Databricks Academy is transitioning to a notebook-based format for classroom sessions within the Databricks environment, discontinuing the use of slide decks for lectures. You can access the lecture notebooks in the Vocareum lab environment.


1. Data Ingestion with Lakeflow Connect

This course provides a comprehensive introduction to Lakeflow Connect, a scalable and simplified solution for ingesting data into Databricks from a wide range of sources. You’ll begin by exploring the different types of Lakeflow Connect connectors (Standard and Managed) and learn various data ingestion techniques, including batch, incremental batch, and streaming ingestion. You'll also review the key benefits of using Delta table and the Medallion architecture


Next, you’ll develop practical skills for ingesting data from cloud object storage using Lakeflow Connect Standard Connectors. This includes working with methods such as CREATE TABLE AS SELECT (CTAS), COPY INTO, and Auto Loader, with an emphasis on the benefits and considerations of each approach. You’ll also learn how to append metadata columns to your bronze-level tables during ingestion into the Databricks Data Intelligence Platform. The course then covers how to handle records that don’t match your table schema using the rescued data column, along with strategies for managing and analyzing this data. You’ll also explore techniques for ingesting and flattening semi-structured JSON data.


Following this, you’ll explore how to perform enterprise-grade data ingestion using Lakeflow Connect Managed Connectors to bring in data from databases and Software-as-a-Service (SaaS) applications. The course also introduces Partner Connect as an option for integrating partner tools into your ingestion workloads.


Finally, the course wraps up with alternative ingestion strategies, including MERGE INTO operations and leveraging the Databricks Marketplace, equipping you with a strong foundation to support modern data engineering use cases.


2. Deploy Workloads with Lakeflow Jobs

Deploy Workloads with Lakeflow Jobs course teaches how to orchestrate and automate data, analytics, and AI workflows using Lakeflow Jobs as a unified orchestration platform within the Databricks ecosystem. 

You will learn to design and implement data workloads using Directed Acyclic Graphs (DAGs), configure various scheduling options, and implement advanced workflow features such as conditional task execution, run-if dependencies, and for each loops. 

The course covers best practices for creating robust, production-ready pipelines with proper compute selection, modular orchestration, error handling techniques, and fault-tolerant design-all natively integrated within the Databricks Data Intelligence Platform.


3. Build Data Pipelines with Apache Spark Declarative Pipelines

This course introduces users to the essential concepts and skills needed to build data pipelines using Apache Spark Declarative Pipelines (SDP) in Databricks for incremental batch or streaming ingestion and processing through multiple streaming tables and materialized views. Designed for data engineers new to Spark Declarative Pipelines, the course provides a comprehensive overview of core components such as incremental data processing, streaming tables, materialized views, and temporary views, highlighting their specific purposes and differences.


Topics covered include:

Developing and debugging ETL pipelines with the multi-file editor in Spark Declarative Pipelines using SQL (with Python code examples provided)

How Spark Declarative Pipelines track data dependencies in a pipeline through the pipeline graph

Configuring pipeline compute resources, data assets, trigger modes, and other advanced options


Next, the course introduces data quality expectations in Spark Declarative Pipelines, guiding users through the process of integrating expectations into pipelines to validate and enforce data integrity. Learners will then explore how to put a pipeline into production, including scheduling options, and enabling pipeline event logging to monitor pipeline performance and health.


Finally, the course covers how to implement Change Data Capture (CDC) using the AUTO CDC INTO syntax within Spark Declarative Pipelines to manage slowly changing dimensions (SCD Type 1 and Type 2), preparing users to integrate CDC into their own pipelines.


4. DevOps Essentials for Data Engineering

This course explores software engineering best practices and DevOps principles, specifically designed for data engineers working with Databricks. Participants will build a strong foundation in key topics such as code quality, version control, documentation, and testing. The course emphasizes DevOps, covering core components, benefits, and the role of continuous integration and delivery (CI/CD) in optimizing data engineering workflows.


You will learn how to apply modularity principles in PySpark to create reusable components and structure code efficiently. Hands-on experience includes designing and implementing unit tests for PySpark functions using the pytest framework, followed by integration testing for Databricks data pipelines with Spark Declarative Pipeline and Jobs to ensure reliability.


The course also covers essential Git operations within Databricks, including using Databricks Git Folders to integrate continuous integration practices. Finally, you will take a high level look at various deployment methods for Databricks assets, such as REST API, CLI, SDK, and Declarative Automation Bundles (DABs), providing you with the knowledge of techniques to deploy and manage your pipelines.


By the end of the course, you will be proficient in software engineering and DevOps best practices, enabling you to build scalable, maintainable, and efficient data engineering solutions.

Skill Level
Associate
Duration
16h
Prerequisites

1. Data Ingestion with Lakeflow Connect

Basic understanding of the Databricks Data Intelligence platform, including Databricks Workspaces, Apache Spark, Delta Lake, the Medallion Architecture and Unity Catalog.

Basic understanding of data ingestion workflows (batch, streaming, incremental) and general ETL principles

Experience working with various file formats (e.g., Parquet, CSV, JSON, TXT).

Proficiency in SQL and Python.

Familiarity with running code in Databricks notebooks.


2. Deploy Workloads with Lakeflow Jobs

Completion of the course "Get Started with Databricks for Data Engineering", or a solid understanding of the Databricks Data Intelligence Platform

Basic Understanding of topics like navigating a Databricks Workspace, Apache Spark, Delta Lake, Medallion Architecture, and Unity Catalog.

Familiarity with python/pyspark

Experience in writing intermediate-level SQL queries.


3. Build Data Pipelines with Apache Spark Declarative Pipelines

Basic understanding of the Databricks Data Intelligence platform, including Databricks Workspaces, Apache Spark, Delta Lake, the Medallion Architecture, Lakeflow Jobs and Unity Catalog.

Experience ingesting raw data into Delta tables, including using the read_files SQL function to load formats like CSV, JSON, TXT, and Parquet.

Proficiency in transforming data using SQL, including writing intermediate-level queries and a basic understanding of SQL joins.

Understanding of ETL concepts, and batch/streaming workflows.


4. DevOps Essentials for Data Engineering

Proficient knowledge of the Databricks platform, including experience with Databricks Workspaces, Apache Spark, Delta Lake and the Medallion Architecture, Unity Catalog, Delta Live Tables, and Workflows. A basic understanding of Git version control is also required.

Experience ingesting and transforming data, with proficiency in PySpark for data processing and DataFrame manipulations. Additionally, candidates should have experience writing intermediate level SQL queries for data analysis and transformation.

Knowledge of Python programming, with proficiency in writing intermediate level Python code, including the ability to design and implement functions and classes. Users should also be skilled in creating, importing, and effectively utilizing Python packages.

Outline

1. Data Ingestion with Lakeflow Connect

Data Engineering in Databricks

Exploring the Lab Environment

Data Ingestion from Cloud Storage

Demo - Data Ingestion with CREATE TABLE AS and COPY INTO

Demo - Create Streaming Tables with SQL using Auto Loader

Appending Metadata Columns on Ingest

Demo - Adding Metadata Columns During Ingestion

Working with the Rescued Data Column

Demo - Handling CSV Ingestion with the Rescued Data Column

Lab - Creating Bronze Tables from CSV Files

Ingesting Semi-Structured Data: JSON

Demo - Ingesting JSON Files with Databricks

Lab - Creating Bronze Tables from JSON Files

Ingesting Enterprise Data Overview

Demo - Enterprise Data Ingestion with LakeFlow Connect

Additional Features and Ingesting into Existing Delta Tables

Demo - BONUS - Data Ingestion with MERGE INTO


2. Deploy Workloads with Lakeflow Jobs

• Introduction to Data Engineering in Databricks

• Lakeflow Jobs Core Components

• Course Project Overview

• Demo: Creating a Job Using the Lakeflow Jobs UI

• Lab: Create your First Job

• Creating and Scheduling Jobs

• Demo: Automating Workloads with Scheduling and Triggers

• Conditional and Iterative Task

• Demo: Building Dynamic Workloads with Advanced Tasks

• Lab: Adding If-Else Task and Automating your Job

• Handling Task Failures and Monitoring Jobs Performance

• Demo: Monitoring and Repairing Task

• Lakeflow Jobs in Production and Best Practices

• BONUS LAB: Modular Orchestration


3. Build Data Pipelines with Apache Spark Declarative Pipelines

• Introduction to Data Engineering in Databricks

• Demo: Course Setup and Creating a Pipeline

• Course Project and Dataset Types Overview

• Simplified Pipeline Development and Common Pipeline Settings

• Demo: Developing a Simple Pipeline

• Ensure Data Quality with Expectations

• Demo: Adding Data Quality Expectations

• Lab: Create a Pipeline

• Streaming Joins and Deploying Pipelines to Production

• Demo: Deploying a Pipeline to Production

• Change Data Capture (CDC) Overview

• Demo: Change Data Capture with AUTO CDC with SCD TYPE 1

• Bonus Lab: AUTO CDC INTO with SCD Type 1



4. DevOps Essentials for Data Engineering

Continuous Integration (CI)

• Introduction to Software Engineering (SWE) Best Practices

• Introduction to Modularizing PySpark Code

• Demo: Modularizing PySpark Code - REQUIRED

• Lab: Modularize PySpark Code

• DevOps Fundamentals

• The Role of CI and CD in DevOps

• Planning the Project

• Demo: Project Setup Exploration

• Introduction to Unit Tests for PySpark

• Demo: Creating and Executing Unit Tests

• Lab: Create and Execute Unit Tests

• Executing Integration Tests with SDP and Jobs

• Demo: Performing Integration Tests

• Version Control with Git Overview

• Lab: Version Control with Databricks Git Folders and GitHub


Continuous Deployment (CD)

• Deploying Databricks Assets Overview

• Demo: Deploying the Databricks Assets

Upcoming Public Classes

Date
Time
Your Local Time
Language
Price
Jul 28 - 29
09 AM - 05 PM (Australia/Sydney)
-
English
$1500.00
Aug 05 - 06
09 AM - 05 PM (America/New_York)
-
English
$1500.00
Sep 01 - 02
09 AM - 05 PM (Europe/London)
-
English
$1500.00
Sep 01 - 02
09 AM - 05 PM (America/New_York)
-
English
$1500.00
Sep 08 - 09
09 AM - 05 PM (Asia/Kolkata)
-
English
$1500.00
Sep 15 - 16
09 AM - 05 PM (America/Los_Angeles)
-
English
$1500.00
Oct 06 - 07
09 AM - 05 PM (Europe/London)
-
English
$1500.00
Oct 06 - 07
09 AM - 05 PM (America/New_York)
-
English
$1500.00
Oct 13 - 14
09 AM - 05 PM (Asia/Kolkata)
-
English
$1500.00
Oct 21 - 22
09 AM - 05 PM (America/Los_Angeles)
-
English
$1500.00

Public Class Registration

If your company has purchased success credits or has a learning subscription, please fill out the Training Request form. Otherwise, you can register below.

Private Class Request

If your company is interested in private training, please submit a request.

See all our registration options

Registration options

Databricks has a delivery method for wherever you are on your learning journey

Runtime

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Register now

Instructors

Instructor-Led

Public and private courses taught by expert instructors across half-day to two-day courses

Register now

Learning

Blended Learning

Self-paced and weekly instructor-led sessions for every style of learner to optimize course completion and knowledge retention. Go to Subscriptions Catalog tab to purchase

Purchase now

Scale

Skills@Scale

Comprehensive training offering for large scale customers that includes learning elements for every style of learning. Inquire with your account executive for details

Upcoming Public Classes

Generative AI Engineer

Generative AI Engineering with Databricks - Spanish

Este curso está dirigido a científicos de datos, ingenieros de machine learning y otros profesionales de datos que desean crear aplicaciones de IA generativa utilizando los frameworks más recientes y populares y las funcionalidades de Databricks.

Nota: Databricks Academy está migrando a un formato basado en notebooks para las sesiones en el aula dentro del entorno de Databricks, y deja de utilizar diapositivas para las clases. Puede acceder a los notebooks de las clases en el entorno de laboratorio de Vocareum.

A continuación, describimos cada uno de los cuatro módulos de cuatro horas incluidos en este curso.

Building RAG Agents with Agent Bricks: este curso ofrece capacitación práctica para crear agentes de recuperación utilizando Databricks Agent Bricks. Los participantes aprenderán a explorar y consultar Knowledge Assistants, analizar documentos no estructurados para convertirlos en datos estructurados mediante AI Functions, dividir texto en fragmentos (chunks) para la recuperación semántica, crear índices de Vector Search y crear Knowledge Assistants listos para producción respaldados por múltiples fuentes de conocimiento.

Building Agentic Applications on Databricks: este curso enseña a los estudiantes a crear aplicaciones agénticas de nivel de producción en Databricks. Los estudiantes aprenden a crear herramientas de agente gobernadas mediante Unity Catalog y MCP, crear sistemas de agente único y multiagente con el OpenAI Agents SDK, y aprovechar Agent Bricks y Genie para casos de uso de knowledge assistant orquestados con un agente supervisor. El curso abarca toda la progresión, desde la creación de prototipos de herramientas hasta la implementación en producción, con experiencia práctica utilizando el rastreo (tracing) de MLflow para observar la ejecución del agente.

Agent Evaluation on Databricks: este curso enseña a los estudiantes a evaluar sistemáticamente agentes de IA utilizando el framework de evaluación de MLflow, abordando los desafíos únicos de los sistemas de IA no deterministas que las pruebas de software tradicionales no pueden manejar. Los estudiantes aprenden a implementar diversos enfoques de evaluación, incluidos los jueces integrados (built-in judges) para criterios comunes como la corrección y la seguridad, los jueces basados en directrices para requisitos específicos del negocio y los jueces personalizados para necesidades especializadas. El curso abarca tanto la evaluación sin conexión utilizando conjuntos de datos (datasets) seleccionados como el monitoreo de producción en línea, con experiencia práctica utilizando las capacidades de rastreo (tracing) de MLflow para comprender los patrones de ejecución del agente y recopilar retroalimentación humana de diferentes tipos de partes interesadas. A través de demostraciones y laboratorios prácticos, los estudiantes desarrollan habilidades para crear flujos de trabajo de evaluación que impulsan mejoras continuas de calidad a lo largo del ciclo de vida de desarrollo de los agentes de IA.

Deploying and Monitoring Agent Applications on Databricks: este curso abarca el ciclo de vida completo para implementar y monitorear agentes de IA generativa en Databricks. Los participantes aprenderán a implementar agentes como Databricks Apps utilizando Declarative Automation Bundles (DABs), integrar herramientas mediante el Model Context Protocol (MCP), instrumentar agentes con MLflow Tracing y evaluar la calidad en producción utilizando scorers, jueces de múltiples turnos y evaluación en línea. A través de demos y laboratorios prácticos, los participantes adquirirán experiencia práctica en la creación, observación y monitoreo de agentes de IA de nivel de producción en la plataforma Databricks.

Paid
16h
Lab
instructor-led
Associate
Generative AI Engineer

Generative AI Engineering with Databricks - French

Ce cours s’adresse aux data scientists, aux ingénieurs en machine learning et aux autres professionnels des données qui souhaitent créer des applications d’IA générative à l’aide des frameworks les plus récents et les plus populaires et des fonctionnalités de Databricks.

Remarque : Databricks Academy passe à un format basé sur des notebooks pour les sessions en classe dans l’environnement Databricks, et n’utilise plus de diaporamas pour les cours. Vous pouvez accéder aux notebooks de cours dans l’environnement de laboratoire Vocareum.

Ci-dessous, nous décrivons chacun des quatre modules de quatre heures inclus dans ce cours.

Building RAG Agents with Agent Bricks : ce cours propose une formation pratique à la création d’agents de récupération à l’aide de Databricks Agent Bricks. Les participants apprendront à explorer et à interroger les Knowledge Assistants, à analyser des documents non structurés pour les convertir en données structurées à l’aide des AI Functions, à découper le texte en fragments (chunks) pour la récupération sémantique, à créer des index Vector Search et à créer des Knowledge Assistants prêts pour la production s’appuyant sur plusieurs sources de connaissances.

Building Agentic Applications on Databricks : ce cours enseigne aux étudiants comment créer des applications agentiques de niveau production sur Databricks. Les étudiants apprennent à créer des outils d’agent gouvernés à l’aide d’Unity Catalog et de MCP, à créer des systèmes à agent unique et multi-agents avec l’OpenAI Agents SDK, et à exploiter Agent Bricks et Genie pour des cas d’usage de knowledge assistant orchestrés avec un agent superviseur. Le cours couvre l’ensemble de la progression, du prototypage des outils au déploiement en production, avec une expérience pratique de l’utilisation du traçage (tracing) MLflow pour observer l’exécution des agents.

Agent Evaluation on Databricks : ce cours enseigne aux étudiants comment évaluer systématiquement les agents IA à l’aide du cadre d’évaluation de MLflow, en relevant les défis propres aux systèmes d’IA non déterministes que les tests logiciels traditionnels ne peuvent pas gérer. Les étudiants apprennent à mettre en œuvre diverses approches d’évaluation, notamment les juges intégrés (built-in judges) pour des critères courants tels que l’exactitude et la sécurité, les juges basés sur des directives pour des exigences propres à l’entreprise, et les juges personnalisés pour des besoins spécialisés. Le cours couvre à la fois l’évaluation hors ligne à l’aide d’ensembles de données (datasets) sélectionnés et la surveillance de la production en ligne, avec une expérience pratique de l’utilisation des capacités de traçage (tracing) de MLflow pour comprendre les schémas d’exécution des agents et recueillir les retours humains de différents types de parties prenantes. Grâce à des démonstrations et des laboratoires pratiques, les étudiants développent des compétences pour créer des flux de travail d’évaluation qui favorisent l’amélioration continue de la qualité tout au long du cycle de vie de développement des agents IA.

Deploying and Monitoring Agent Applications on Databricks : ce cours couvre le cycle de vie de bout en bout pour le déploiement et la surveillance des agents d’IA générative sur Databricks. Les participants apprendront à déployer des agents en tant que Databricks Apps à l’aide des Declarative Automation Bundles (DABs), à intégrer des outils via le Model Context Protocol (MCP), à instrumenter les agents avec MLflow Tracing, et à évaluer la qualité en production à l’aide de scorers, de juges multi-tours et de l’évaluation en ligne. Grâce à des démos et des laboratoires pratiques, les participants acquerront une expérience pratique de la création, de l’observation et de la surveillance d’agents IA de niveau production sur la plateforme Databricks.

Paid
16h
Lab
instructor-led
Associate

Questions?

If you have any questions, please refer to our Frequently Asked Questions page.