Build, evaluate and deploy RAG apps with Databricks generative AI training in 2027.

Generative AI Engineering with Databricks is a 2-day, HRD Corp Claimable course from Trainocate.

It covers retrieval-augmented generation (RAG), Vector Search, LLM evaluation and governance, and deployment with Mosaic AI, preparing you for the Databricks Certified Generative AI Engineer Associate exam.

  • Why get trained: Ground LLM answers in your company’s data, measure answer quality before launch and run GenAI apps that are governed and monitored.
  • Why it matters: GenAI prototypes often stall before launch because answers are inaccurate, ungoverned or impossible to monitor at scale.
  • Who should attend: Data scientists, ML engineers and AI practitioners with basic Python and SQL skills who build LLM-powered applications.

Turn your GenAI ideas into working applications. Enroll in Generative AI Engineering with Databricks and launch RAG apps your business can rely on in 2027.

Trainocate is a Databricks Authorized Training Partner and a Training Industry Top 20 IT and Technical Training Company for six consecutive years.

Overview

This course is aimed at data scientists, machine learning engineers, and other data practitioners who want to build generative AI applications using the latest and most popular frameworks and Databricks capabilities.

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

Generative AI Solution Development: This is your introduction to contextual generative AI solutions using the retrieval-augmented generation (RAG) method. First, you’ll be introduced to RAG architecture and the significance of contextual information using Mosaic AI Playground. Next, we’ll show you how to prepare data for generative AI solutions and connect this process with building a RAG architecture. Finally, you’ll explore concepts related to context embedding, vectors, vector databases, and the utilization of Mosaic AI Vector Search.

Generative AI Application Development: Ready for information and practical experience in building advanced LLM applications using multi-stage reasoning LLM chains and agents? In this module, you’ll first learn how to decompose a problem into its components and select the most suitable model for each step to enhance business use cases. Following this, we’ll show you how to construct a multi-stage reasoning chain utilizing LangChain and HuggingFace transformers. Finally, you’ll be introduced to agents and will design an autonomous agent using generative models on Databricks.

Generative AI Application Evaluation and Governance: This is your introduction to evaluating and governing generative AI systems. First, you’ll explore the meaning behind and motivation for building evaluation and governance/security systems. Next, we’ll connect evaluation and governance systems to the Databricks Data Intelligence Platform. Third, we’ll teach you about a variety of evaluation techniques for specific components and types of applications. Finally, the course will conclude with an analysis of evaluating entire AI systems with respect to performance and cost.

Generative AI Application Deployment and Monitoring: Ready to learn how to deploy, operationalize, and monitor generative deploying, operationalizing, and monitoring generative AI applications? This module 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.

Skills Covered

  • Generative AI Solution Development
  • Generative AI Application Development
  • Generative AI Application Evaluation and Governance
  • Generative AI Application Deployment and Monitoring

Prerequisites

The content was developed for participants with these skills/knowledge/abilities:

1. Building RAG Agents with Agent Bricks

• Basic SQL knowledge for querying tables and using built-in functions
• Basic Python programming experience
• Familiarity with the Databricks workspace UI (e.g. navigating Unity Catalog)
• Understanding of Unity Catalog concepts including catalogs, schemas, and volumes
• Familiarity with fundamental LLM concepts (e.g. embeddings, retrieval-augmented generation)
• Understanding of structured vs unstructured data

2. Building Agentic Applications on Databricks

Python-Specific Skills:

• Basic Python syntax and data structures
• Understanding of functions, classes, and decorators
• Experience with Python package management and imports
• Familiarity with JSON data handling
• Basic understanding of async/await patterns

SQL-Specific Skills:

• Basic SQL query syntax (SELECT, FROM, WHERE)
• Understanding of SQL functions and user-defined functions
• Experience with Unity Catalog SQL functions

Databricks-Specific Skills:

• Understanding of Databricks workspace navigation and notebook interface
• Knowledge of Unity Catalog structure (catalogs, schemas, tables, volumes, functions)
• Experience with Databricks compute resources and serverless computing
• Familiarity with MLflow experiment tracking
• Understanding of Databricks model serving endpoints

GenAI/Agent-Specific Skills:

• Basic understanding of LLMs and their capabilities
• Knowledge of prompt engineering and system prompts
• Familiarity with tool-calling agents and function calling concepts
• Basic awareness of the Model Context Protocol (MCP)

3. Agent Evaluation on Databricks

• Intermediate Python programming experience
• Basic SQL knowledge for querying and creating functions
• Familiarity with Databricks Data Intelligence Platform
• Understanding of Unity Catalog concepts including catalogs and schemas
• Basic understanding of large language models (LLMs) and prompt engineering
• Basic knowledge of MLflow

4. Deploying and Monitoring Agent Applications on Databricks

• Familiarity with Databricks workspace and notebooks
• Familiarity with Unity Catalog
• Experience building agents using the OpenAI Agents SDK
• Basic knowledge of MLflow and Python
• Familiarity with GenAI agent concepts (LLM calls, tool invocation, retrieval)

Target Audience

  • Everyone who is interested

Course Curriculum

Module 1: Building RAG Agents with Agent Bricks

Retrieval Agents and Lakebase Search

  • Retrieval Agents and Lakebase Search on Databricks
  • Demo: Creating a Genie Agent for Unstructured Data
  • Lab: Information Retrieval with Lakebase Search

Document Parsing and Chunking Strategies

  • Document Parsing and Chunking Strategies
  • Demo: Transforming PDFs to Structured Data

AI Search on Databricks

  • AI Search on Databricks
  • Lab: Chunking PDFs and AI Search

Module 2: Building Agentic Applications on Databricks

Foundations

  • Agents, MCP, and AI Governance on Databricks
  • Demo: Building Agent Tools on Databricks
  • Lab: Assessing and Fixing Agent Tools

Building Agents with the OpenAI Agents SDK

  • Building Agents with Popular Frameworks on Databricks
  • Demo: Introduction to OpenAI Agents SDK on Databricks
  • Lab: Multi-Agent Orchestration with the OpenAI Agents SDK on Databricks

Other Frameworks

  • Demo: Introduction to LangChain on Databricks
  • Lab: Building Agents with DSPy on Databricks

Module 3: Agent Evaluation on Databricks

AI Agent Evaluation Fundamentals

  • The Challenge of Evaluating AI Agents
  • Demo: Agent Setup
  • MLflow’s Evaluation Framework

AI Agent Evaluation Fundamentals

  • Built-In Judges
  • Demo: Using MLflow Built-In Judges
  • Guideline Judges
  • Demo: Guideline Judges with MLflow
  • Custom Judges and Feedback
  • Demo: Custom Judges with MLflow
  • Lab: Applying Agent Evaluation

Custom Judges and Human Feedback

  • Offline vs. Online Evaluation Strategies
  • Lab: Developer and SME Feedback with MLflow

Module 4: Deploying and Monitoring Agent Applications on Databricks

Agent Deployment

  • Agent Deployment on Databricks
  • Demo: Deploying an Observable Agent

Tool Integration and Observability

  • Tool Integration and Observability
  • Demo: Tracing for Production Agents

Production Evaluation and Monitoring

  • Production Evaluation and Monitoring
  • Lab: Online Evaluation with Multi-Turn Conversations
  • Lab: Backfilling and Archiving Multi-Turn Conversations

Dates & Locations

Let’s make it work for you

Can’t find a date that fits? Need to train your whole team? Looking for a discount?
Speak to one of our learning experts today.

February 25, 2027 - February 26, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

February 25, 2027 - February 26, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900

April 19, 2027 - April 20, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

April 19, 2027 - April 20, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900

June 16, 2027 - June 17, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

June 16, 2027 - June 17, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900

August 25, 2027 - August 26, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

August 25, 2027 - August 26, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900

October 19, 2027 - October 20, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

October 19, 2027 - October 20, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900

December 6, 2027 - December 7, 2027

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
Exam:
RM 900

December 6, 2027 - December 7, 2027

Location: Online
Modal: VILT
Availability: TBC
Exam:
RM 900
Trainocate exam and cert

Exam & Certification

Databricks Certified Generative AI Engineer Associate.

The Databricks Certified Generative AI Engineer Associate certification exam assesses an individual’s ability to design and implement LLM-enabled solutions using Databricks. This includes problem decomposition to break down complex requirements into manageable tasks as well as choosing appropriate models, tools and approaches from the current generative AI landscape for developing comprehensive solutions.

It also assesses Databricks-specific tools such as Vector Search for semantic similarity searches, Model Serving for deploying models and solutions, MLflow for managing a solution lifecycle, and Unity Catalog for data governance. Individuals who pass this exam can be expected to build and deploy performant RAG applications and LLM chains that take full advantage of Databricks and its toolset.

The exam covers:

  • Design Applications – 14%
  • Data Preparation – 14%
  • Application Development – 30%
  • Assembling and Deploying Apps – 22%
  • Governance – 8%
  • Evaluation and Monitoring – 12%

Training & Certification Guide

Frequently Asked Questions

Speak to a Training Consultant

All courses are HRD Claimable.
Get in touch with our team via the form or WhatsApp us on +6011-5119 6631

Preferred mode of training
Checkboxes