Note: This course has been retired and is no longer available. Please explore our latest NVIDIA courses for updated training and certification options.

With the incredible capabilities of Large Language Models (LLMs), enterprises are eager to integrate them into their products and applications for use cases like text generation, large-scale document analysis, and chatbot assistants. 

The fastest way to begin leveraging LLMs is through prompt engineering, a foundational technique that underpins advanced methods such as Retrieval-Augmented Generation (RAG) and Parameter-Efficient Fine-Tuning (PEFT). 

In this instructor-led workshop, participants will work with NVIDIA’s NIM deployment of Llama 3.1 alongside the popular LangChain library. Through practical, hands-on projects, learners will gain the skills to design, build, and deploy powerful LLM-based applications using prompt engineering. 

After completing this course, participants will be able to:

  • Apply iterative prompt engineering best practices to create robust LLM applications.
  • Use LangChain to organize, compose, and optimize LLM workflows.
  • Write Python application code for generative tasks, document analysis, and chatbot development.
  • Build applications leveraging structured outputs from LLMs.
  • Develop and integrate LLM-powered agents capable of tool use and real-time data integration.
  • Deploy NVIDIA LLM NIM with Llama 3.1 for scalable enterprise-ready applications.

Key Features:

  • Gain hands-on prompt engineering experience by crafting and refining prompts to build applications for generation, analysis, and chatbots.

     

  • Learn to build reusable LLM workflows with LangChain and efficiently deploy Llama 3.1 using NVIDIA NIM.

  • Apply your skills to real-world use cases such as document tagging, structured outputs, persona-driven chatbots, and tool integration.

  • Build practical skills through module-wise mini-projects and a final project integrating prompts, LangChain, structured outputs, and agentic tools.

  • Earn an NVIDIA DLI certificate to validate your practical GenAI skills.

Who should Attend?

  • Python developers exploring LLM application development
  • Data scientists and AI engineers
  • Solution architects designing enterprise generative AI solutions
  • Technical professionals seeking to integrate LLMs into workflows

Prerequisites:

  • Intermediate-level Python programming skills
  • Basic understanding of LLM fundamentals (tokenization, embeddings, etc.)
  • Familiarity with APIs and JSON-based workflows recommended

Why choose CloudThat as your training partner?

  • NVIDIA-Certified Training Partner with expertise in Generative AI.
  • Industry-recognized trainers with real-world AI/ML experience.
  • Hands-on learning with GPU-powered cloud environments provided.
  • Customized learning paths for both beginners and advanced professionals.
  • Interactive sessions with live coding, mini-projects, and Q&A.
  • Career support through guidance on AI roles and certification pathways.
  • Always up-to-date content reflecting NVIDIA’s cutting-edge LLM technologies.

Course Outline: Download Course Outline

  • Orient to the main worshop topics, schedule and prerequisites.
  • Learn why prompt engineering is core to interacting with Large Languange Models (LLMs).
  • Discuss how prompt engineering can be used to develop many classes of LLM-based applications.
  • Learn about NVIDIA LLM NIM, used to deploy the Llama 3.1 LLM used in the workshop.

  • Get familiar with the workshop environment.
  • Create and view responses from your first prompts using the OpenAI API, and LangChain.
  • Learn how to stream LLM responses, and send LLMs prompts in batches, comparing differences in performance.
  • Begin practicing the process of iterative prompt development.
  • Create and use your first prompt templates.
  • Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs.

  • Learn about LangChain runnables, and the ability to compose them into chains using LangChain Expression Language (LCEL).
  • Write custom functions and convert them into runnables that can be included in LangChain chains.
  • Compose multiple LCEL chains into a single larger application chain.
  • Exploit opportunities for parallel work by composing parallel LCEL chains.
  • Do a mini project where to perform a combination of analysis and generative tasks on a batch of inputs using LCEL and parallel execution.

  • Learn about two of the core chat message types, human and AI messages, and how to use them explictly in application code.
  • Provide chat models with instructive examples by way of a technique called few-shot prompting.
  • Work explicitly with the system message, which will allow you to define an overarching persona and role for your chat models.
  • Use chain-of-thought prompting to augment your LLMs ability to perform tasks requiring complex reasoning.
  • Manage messages to retain conversation history and enable chatbot functionality.
  • Do a mini-project where you build a simple yet flexible chatbot application capable of assuming a variety of roles.

  • Explore some basic methods for using LLMs to generate structured data in batch for downstream use.
  • Generate structured output through a combination of Pydantic classes and LangChain's `JsonOutputParser`.
  • Learn how to extract data and tag it as you specify out of long form text.
  • Do a mini-project where you use structured data generation techniques to perform data extraction and document tagging on an unstructured text document.

  • Create LLM-external functionality called tools, and make your LLM aware of their availability for use.
  • Create an agent capable of reasoning about when tool use is appropriate, and integrating the result of tool use into its responses.
  • Do a mini-project where you create an LLM agent capable of utilizing external API calls to augment its responses with real-time data.

  • Review key learnings and answer questions.
  • Earn a certificate of competency for the workshop.
  • Complete the workshop survey.
  • Get recommendations for the next steps to take in your learning journey.

Certification Details:

    Participants who complete all modules and final project will receive an NVIDIA DLI Certificate of Competency in LLM Application Development.

Click to Zoom

FAQs:

Developers, data scientists, and AI engineers interested in applying prompt engineering for enterprise-ready LLM solutions.

Basic familiarity with LLM concepts is recommended, but deep ML expertise is not required.

NVIDIA NIM, LangChain, Llama 3.1, Pydantic, and agentic frameworks.

A 1-day, instructor-led workshop with lectures, hands-on labs, and coding projects.

Yes, every module includes coding labs and mini-projects, culminating in a final integrated application.

AI/ML professionals with LLM expertise typically earn 30–50% higher salaries than traditional software engineers, depending on role and region.

Yes, an NVIDIA DLI Certificate of Competency upon successful completion.

A laptop with Chrome/Firefox. NVIDIA provides cloud-based GPU-accelerated servers for hands-on labs.

It is designed for Python developers with intermediate coding skills; prior LLM exposure is helpful but not mandatory.

It provides practical, industry-relevant skills in Generative AI and prompt engineering, opening opportunities in AI engineering, solution architecture, and applied NLP.

Talk to Us