Rapid Application Development with Large Language Models (LLMs)
NVIDIA Deep Learning Institute
Last updated June 18, 2026
Rapid Application Development with Large Language Models is an eight-hour, hands-on course from NVIDIA's Deep Learning Institute that walks developers through building applications on top of pretrained, open-source language models. Rated at NVIDIA's beginner level for technical learners, it starts from first principles — how transformers process text through tokenizers, embeddings, and attention — and builds up to working with real models from the Hugging Face ecosystem and its Transformers library. Along the way you use encoder models for tasks like embedding, classification, and zero-shot prediction, work with decoder and encoder-decoder models for text generation and translation, and touch multimodal models that bring in images and audio. The course finishes with deployment and scaling concerns and an introduction to orchestrating models and tool-using agents with LangChain, capped by a final project that combines text generation, multimodal work, and orchestration into one application. A practical on-ramp to LLM application development for people who can already code.
What you'll learn
- Working through how a transformer processes text, from tokenizers and embeddings to attention
- Pulling pretrained models from the Hugging Face Transformers library and using encoder models for embedding, classification, and zero-shot tasks
- Using decoder and encoder-decoder models for text generation and tasks like machine translation
- Orchestrating data pipelines and tool-using agents with LangChain, then building a final application that combines generation, multimodal work, and orchestration
Frequently asked questions about Rapid Application Development with Large Language Models (LLMs)
Who is Rapid Application Development with Large Language Models (LLMs) for?
Developers with intermediate Python and a little introductory deep-learning background who want a practical, foundations-first start in building applications on open-source LLMs.
Is Rapid Application Development with Large Language Models (LLMs) free?
No — Rapid Application Development with Large Language Models (LLMs) is a paid course.
What are the prerequisites for Rapid Application Development with Large Language Models (LLMs)?
Introductory deep learning, with comfort using PyTorch and transfer learning preferred (the material covered by DLI's Getting Started with Deep Learning or Fundamentals of Deep Learning, or similar experience, is sufficient). Intermediate Python experience, including object-oriented programming and common libraries, is also expected.
Do you need to code for Rapid Application Development with Large Language Models (LLMs)?
Yes — Rapid Application Development with Large Language Models (LLMs) involves hands-on coding.
Why we suggest this course
This is the gentlest technical entry point into NVIDIA's developer-focused LLM courses: it assembles the foundations — transformers, the Hugging Face Transformers workflow, and a first taste of LangChain orchestration — that the institute's agent and RAG courses then assume you already have. The distinct takeaway is a working grasp of the open-source LLM toolchain end to end, rather than depth in any one technique. Worth knowing before you start: "beginner" here is relative to a developer audience — the prerequisites still expect introductory deep learning and intermediate Python, so it is an on-ramp for coders, not for absolute newcomers to programming.