Generative AI Application Deployment and Monitoring

Ready to learn how to deploy, operationalize, and monitor generative AI applications? This content will help you gain skills in the deployment of generative AI applications using tools like Model Serving. We’ll also cover how to operationalize generative AI applications following best practices and recommended architectures. Finally, we’ll discuss the idea of monitoring generative AI applications and their components using Lakehouse Monitoring.

Languages Available: English | 日本語 | Português BR | 한국어

Skill Level

Associate

Duration

Prerequisites

Familiarity with natural language processing concepts
Familiarity with prompt engineering/prompt engineering best practices
Familiarity with the Databricks Data Intelligence Platform
Familiarity with RAG (preparing data, building a RAG architecture, concepts like embedding, vectors, vector databases, etc.)
Experience with building LLM applications using multi-stage reasoning LLM chains and agents
Familarity with Databricks Data Intelligence Platform tools for evaluation and governance.

Outline

Model Deployment Fundamentals

Model Management
Deployment Methods

Batch Deployment

Introduction to Batch Deployment
Batch Inference
Batch Inference Workflows using SLM

Real-Time Deployment

Introduction to Real-Time Deployment
Databricks Model Serving
Serving External Models with Model Serving
Deploying an LLM Chain to Databricks Model Serving
Custom Model Deployment and A/B Testing

AI System Monitoring

AI Application Monitoring
Online Monitoring an LLM RAG Chain

LLMOps Concepts

MLOps Primer
LLMOps vs MLOps

Upcoming Public Classes

Date	Time	Your Local Time	Language	Price
Date	Time	Your Local Time	Language	Price	Jun 05	01 PM - 05 PM (Europe/London)	-	English	$750.00
Jun 10	08 AM - 12 PM (Asia/Kolkata)	-	English	$750.00
Jul 10	09 AM - 01 PM (Australia/Sydney)	-	English	$750.00
Jul 10	09 AM - 01 PM (America/New_York)	-	English	$750.00

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.

Customer registration Partner registration

Private Class Request

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

Request Private Training

See all our registration options

Upcoming Public Classes

Date	Time	Your Local Time	Language	Price
Date	Time	Your Local Time	Language	Price	Jun 05	01 PM - 05 PM (Europe/London)	-	English	$750.00
Jun 10	08 AM - 12 PM (Asia/Kolkata)	-	English	$750.00
Jul 10	09 AM - 01 PM (Australia/Sydney)	-	English	$750.00
Jul 10	09 AM - 01 PM (America/New_York)	-	English	$750.00

Registration options

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

Self-Paced

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

Instructor-Led

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

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

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

Building ETL Pipelines with SQL

This course teaches how to build production-ready ETL pipelines using pure SQL on the Databricks Data Intelligence Platform. Students learn Streaming Tables with Auto Loader for incremental ingestion, Materialized Views with incremental refresh for Silver-to-Gold transformations, AUTO CDC (FLOW AUTO CDC) for declarative SCD Type 1 and Type 2 dimension management, and Lakeflow Jobs with SQL File tasks for production orchestration. The course follows a realistic retail dataset through the medallion architecture (Bronze → Silver → Gold).

Note: 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.

Apache Spark Developer

Apache Spark™ Programming with Databricks

This course serves as an appropriate entry point to learn Apache Spark Programming with Databricks.

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

Introduction to Apache Spark

This course offers essential knowledge of Apache Spark, with a focus on its distributed architecture and practical applications for large-scale data processing. Participants will explore programming frameworks, learn the Spark DataFrame API, and develop skills for reading, writing, and transforming data using Python-based Spark workflows.

Developing Applications with Apache Spark

Master scalable data processing with Apache Spark in this hands-on course. Learn to build efficient ETL pipelines, perform advanced analytics, and optimize distributed data transformations using Spark’s DataFrame API. Explore grouping, aggregation, joins, set operations, and window functions. Work with complex data types like arrays, maps, and structs while applying best practices for performance optimization.

Stream Processing and Analysis with Apache Spark

Learn the essentials of stream processing and analysis with Apache Spark in this course. Gain a solid understanding of stream processing fundamentals and develop applications using the Spark Structured Streaming API. Explore advanced techniques such as stream aggregation and window analysis to process real-time data efficiently. This course equips you with the skills to create scalable and fault-tolerant streaming applications for dynamic data environments.

Monitoring and Optimizing Apache Spark Workloads on Databricks

This course explores the Lakehouse architecture and Medallion design for scalable data workflows, focusing on Unity Catalog for secure data governance, access control, and lineage tracking. The curriculum includes building reliable, ACID-compliant pipelines with Delta Lake. You'll examine Spark optimization techniques, such as partitioning, caching, and query tuning, and learn performance monitoring, troubleshooting, and best practices for efficient data engineering and analytics to address real-world challenges.

Languages Available: English | 日本語 | 한국어

Machine Learning Practitioner

Machine Learning Model Development

This comprehensive course provides a practical guide to developing traditional machine learning models on Databricks, emphasizing hands-on demonstrations and workflows using popular ML libraries. Participants will explore key ML techniques, including regression and clustering, while leveraging Databricks’ powerful capabilities. The course covers MLflow integration for model tracking, Databricks Feature Store for feature management, and Optuna for hyperparameter tuning. Additionally, participants will learn how to accelerate model training with Databricks AutoML. By the end of the course, learners will have real-world, practical skills to develop, optimize, and deploy machine learning models efficiently in the Databricks environment.

Languages Available: English | 日本語 | Português BR | 한국어