NVIDIA DLI–Building LLM Applications with Prompt Engineering
Key information
Upcoming sessions
Would you like to schedule this training on a specific date? Contact us by email or via the contact form.
Description of the training: NVIDIA DLI–Building LLM Applications with Prompt Engineering
Prompt engineering is the practice of designing, structuring and iterating prompts to reliably obtain the desired behaviour from an LLM (GPT, LLaMA, Mistral, etc.), without retraining the model.
What is the difference between prompt engineering, fine-tuning and RAG?Prompt engineering only changes the instruction sent to the model (low cost, fast iteration). RAG adds retrieval from external documents at query time. Fine-tuning retrains the model on specific data (highest cost and effort). This training focuses on prompt engineering.
Which tools and frameworks are covered?LLM APIs (including NVIDIA NeMo and major models), LangChain for orchestration (chains, agents, tools), and supporting tooling to build chatbots, pipelines and structured-extraction applications.
How long is this NVIDIA DLI training at MFE-IT?The training lasts 1 day (7 hours), remote with recorded sessions or on-site, ending with the assessment for the NVIDIA DLI certificate.
{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is prompt engineering with LLMs?","acceptedAnswer":{"@type":"Answer","text":"Prompt engineering is the practice of designing, structuring and iterating prompts to reliably obtain the desired behaviour from an LLM (GPT, LLaMA, Mistral, etc.), without retraining the model."}},{"@type":"Question","name":"What is the difference between prompt engineering, fine-tuning and RAG?","acceptedAnswer":{"@type":"Answer","text":"Prompt engineering only changes the instruction sent to the model (low cost, fast iteration). RAG adds retrieval from external documents at query time. Fine-tuning retrains the model on specific data (highest cost and effort). This training focuses on prompt engineering."}},{"@type":"Question","name":"Which tools and frameworks are covered?","acceptedAnswer":{"@type":"Answer","text":"LLM APIs (including NVIDIA NeMo and major models), LangChain for orchestration (chains, agents, tools), and supporting tooling to build chatbots, pipelines and structured-extraction applications."}},{"@type":"Question","name":"How long is this NVIDIA DLI training at MFE-IT?","acceptedAnswer":{"@type":"Answer","text":"The training lasts 1 day (7 hours), remote with recorded sessions or on-site, ending with the assessment for the NVIDIA DLI certificate."}}]} .elementor-accordion .elementor-tab-title .elementor-accordion-icon{margin-right:10px}.elementor-accordion .elementor-tab-title .elementor-accordion-icon + a,.elementor-accordion .elementor-tab-title .elementor-accordion-title{padding-left:4px}Good to know
Our sessions are guaranteed from a single registrant, with no risk of postponement (except in cases of force majeure). A prior interview takes place between the participant and a company representative to fully take into account the participant’s profile (level, needs, professional context, challenges, etc.). Evaluation: during the training, the trainer assesses participants’ learning progress through quizzes, role-plays and practical exercises. Participants receive a certificate of achievement at the end of the training. This training is part of our Artificial Intelligence training catalogue.
Objectives of the training: NVIDIA DLI–Building LLM Applications with Prompt Engineering
- By the end of this training:
- Understand how LLMs work and their generative capabilities.
- Master prompt-engineering techniques: zero-shot, few-shot, chain-of-thought.
- Use LLM APIs to build applications.
- Design pipelines with LangChain and orchestration tools.
- Create chatbots and intelligent assistants.
- Apply security and reliability best practices.
Prerequisites of the training: NVIDIA DLI–Building LLM Applications with Prompt Engineering
Python programming experience (intermediate level). Basic notions of AI and NLP recommended. No specific prior LLM experience required.
Target audience of the training: NVIDIA DLI–Building LLM Applications with Prompt Engineering
Developers wanting to integrate LLMs into their applications. Data scientists and AI engineers. Solution architects evaluating generative AI. Technical project managers leading AI initiatives.
Detailed programme of the training: NVIDIA DLI–Building LLM Applications with Prompt Engineering
Introduction to LLMs
- Transformer architecture and how LLMs work.
- Overview of models: GPT, LLaMA, Mistral, NVIDIA NeMo.
- Tokenisation, context window and generation parameters.
- Lab: first API calls and capability exploration.
Prompt-engineering techniques
- Prompting: zero-shot, one-shot, few-shot.
- Structured prompts with roles and constraints.
- Chain-of-Thought and guided reasoning.
- Handling hallucinations.
- Lab: multi-scenario prompt optimisation.
Building LLM applications
- Orchestration with LangChain: chains, agents, tools.
- Conversational memory and external data sources.
- Building an intelligent chatbot.
- Lab: complete conversational application.
Advanced use cases and deployment
- Information extraction and automatic summarisation.
- Security and governance of LLM applications.
- Production deployment.
- Final assessment for the NVIDIA DLI certificate.
Course highlights
- Focuses on building LLM applications with prompt engineering
- Covers how LLMs work and their generative capabilities
- Delivers a 100% hands-on, GPU-based learning experience
- Awards a recognised NVIDIA DLI certificate
FAQ
What is prompt engineering with LLMs?
Prompt engineering is the practice of designing, structuring and iterating prompts to reliably obtain the desired behaviour from an LLM (GPT, LLaMA, Mistral, etc.), without retraining the model.
What is the difference between prompt engineering, fine-tuning and RAG?
Prompt engineering only changes the instruction sent to the model (low cost, fast iteration). RAG adds retrieval from external documents at query time. Fine-tuning retrains the model on specific data (highest cost and effort). This training focuses on prompt engineering.
Which tools and frameworks are covered?
LLM APIs (including NVIDIA NeMo and major models), LangChain for orchestration (chains, agents, tools), and supporting tooling to build chatbots, pipelines and structured-extraction applications.
How long is this NVIDIA DLI training at MFE-IT?
The training lasts 1 day (7 hours), remote with recorded sessions or on-site, ending with the assessment for the NVIDIA DLI certificate.