Databricks Certified Generative AI Engineer Associate Training

Live Online & Classroom Enterprise Training

Validates skills in building and deploying AI models on Databricks. Covers LLM fine-tuning, RAG, vector databases, and MLflow-based deployment.

Looking for a private batch ?

REQUEST A CALLBACK

Enterprise Reporting
Lifetime Access
CloudLabs
24x7 Support
Real-time code analysis and feedback

What is Databricks Certified Generative AI Engineer Associate Course about?

The Databricks Certified Generative AI Engineer Associate certification validates foundational knowledge and practical skills in generative AI. This course covers key concepts of large language models (LLMs), prompt engineering, embeddings, retrieval-augmented generation (RAG), and integrating AI models with Databricks tools. Through hands-on labs, learners will build, deploy, and optimize generative AI solutions using the Databricks Lakehouse platform. By the end, participants will be ready to demonstrate their ability to work with generative AI applications and prepare for the certification exam.

What are the objectives of Databricks Certified Generative AI Engineer Associate Course ?

Understand the fundamentals of generative AI, LLMs, and embeddings.
Apply prompt engineering techniques for effective AI responses.
Build and deploy RAG pipelines using Databricks.
Work with vector databases for semantic search and knowledge retrieval.
Prepare for and pass the Databricks Certified Generative AI Engineer Associate exam.

Who is Databricks Certified Generative AI Engineer Associate Course for?

Data Scientists and Machine Learning Engineers.
AI/ML Developers exploring LLM applications.
Data Engineers working with Databricks Lakehouse.
Professionals transitioning into generative AI roles.
Students and early-career professionals pursuing AI certifications.

What are the prerequisites for Databricks Certified Generative AI Engineer Associate Course?

Prerequisites:

Basic understanding of Python programming.
Familiarity with machine learning fundamentals.
Awareness of natural language processing (NLP) concepts.
Exposure to Databricks or other cloud-based ML platforms (preferred).
Curiosity and interest in applying AI to real-world use cases.

Learning Path:

Introduction to Generative AI and Large Language Models
Prompt Engineering and Fine-Tuning Basics
Working with Embeddings and Vector Databases
Retrieval-Augmented Generation (RAG) on Databricks
Exam Preparation & Practice Tests for Certification

Related Courses:

Generative AI with Large Language Models (LLMs)
Applied Natural Language Processing with Python
Data Engineering on Databricks
MLOps and Machine Learning Engineering with Databricks

Available Training Modes

Live Online Training

2 Days

Course Outline Expand All

Expand All

Module 1- Design Applications

Design a prompt that elicits a specifically formatted response

Select model tasks to accomplish a given business requirement

Select chain components for a desired model input and output

Translate business use case goals into a description of the desired inputs and outputs for the AI pipeline

Define and order tools that gather knowledge or take actions for multi-stage reasoning

Module 2- Data Preparation

Apply a chunking strategy for a given document structure and model constraints

Filter extraneous content in source documents that degrades quality of a RAG application

Choose the appropriate Python package to extract document content from provided source data and format.

Define operations and sequence to write given chunked text into Delta Lake tables in Unity Catalog

Identify needed source documents that provide necessary knowledge and quality for a given RAG application

Identify prompt/response pairs that align with a given model task

Use tools and metrics to evaluate retrieval performance

Design retrieval systems using advanced chunking strategies.

Explain the role of re-ranking in the information retrieval process.

Apply chunking strategy for a given document structure

Module 3- Application Development

Create tools needed to extract data for a given data retrieval need

Select Langchain/similar tools for use in a Generative AI application.

Identify how prompt formats can change model outputs and results

Qualitatively assess responses to identify common issues such as quality and safety

Select chunking strategy based on model & retrieval evaluation

Augment a prompt with additional context from a user's input based on key fields, terms, and intents

Create a prompt that adjusts an LLM's response from a baseline to a desired output

Implement LLM guardrails to prevent negative outcomes

Write metaprompts that minimize hallucinations or leaking private data

Build agent prompt templates exposing available functions

Select the best LLM based on the attributes of the application to be developed

Select a embedding model context length based on source documents, expected queries, and optimization strategy

Select a model for from a model hub or marketplace for a task based on model metadata/model cards

Select the best model for a given task based on common metrics generated in experiments

Create a prompt that adjusts an LLM's response from a baseline to a desired output

Utilize Agent Framework for developing agentic systems

Select Langchain/similar tools for use in a Generative AI application

Module 4- Assembling and Deploying Applications

Code a chain using a pyfunc model with pre- and post-processing

Control access to resources from model serving endpoints

Code a simple chain according to requirements

Code a simple chain using langchain

Choose the basic elements needed to create a RAG application: model flavor, embedding model, retriever, dependencies, input examples, model signature

Sequence the steps needed to deploy an endpoint for a basic RAG application

Create and query a Vector Search index

Identify how to serve an LLM application that leverages Foundation Model APIs

Identify resources needed to serve features for a RAG application

Explain the key concepts and components of Mosaic AI Vector Search

Create and query a Vector Search index

Identify batch inference workloads and apply ai_query() appropriately

Module 5- Governance

Use masking techniques as guard rails to meet a performance objective

Select guardrail techniques to protect against malicious user inputs to a Gen AI application

Recommend an alternative for problematic text mitigation in a data source feeding a RAG application

Use legal/licensing requirements for data sources to avoid legal risk

Recommend an alternative for problematic text mitigation in a data source feeding a GenAI application

Use masking techniques as guard rails to meet a performance objective

Who is the instructor for this training?

The trainer for this Databricks Certified Generative AI Engineer Associate Training has extensive experience in this domain, including years of experience training & mentoring professionals.

Reviews

My outlook on training changed completely after attending SpringPeople BPC training. The content, the trainer and infrastructure at SpringPeople were top notch and perfectly in tune with the industry requirements. Regardless to say, training is now something that I look forward to to. Kudos to everyone at SpringPeople!

Shweta Priya

Sony

I attended the 3-day AngularJs training at SpringPeople. The trainer was an industry veteran with vast experience in the subject. Notably, the hands-on training, and the Q&A session stood out. Overall, I found SpringPeople a great place to learn with excellent facilities and great trainers. Would recommend SpringPeople to my colleagues and friends.

Swati Singh

I attended the training on API Design for Mulesoft. The sessions were well planned and value-laden. I benefited immensely from the hands-on experience enabled through virtual labs. I would like to specifically commend the efficiency of the support team who were always available to resolve my concerns.

Nikhil Kohli

Stryker

I attended the jQuery training batch, conducted by Mr. Vijay, an SME who did a thorough coverage of all the essentials. He took us through concepts such as jQuery animations, event handlers, plugins, and jQuery-UI by small programs, very easily. The sessions were useful and well structured. By the end of the training, I was well equipped to develop a SPA on Product Management System. Overall, the learning experience at SpringPeople was great!

Heena Rajan

Mindtree