Generative AI and LLMs Training Course – Design, Customise and Deploy Powerful Models

Reference : PH-LLM

1145 € excl. VAT

2 Days

14 h

Each session will take place even if only one person is registered (except in cases of force majeure).

Description of the Generative AI and LLMs Training Course

Large Language Models (LLMs) such as GPT, Claude or Mistral are transforming how we interact with technology. But between their theoretical potential and real-world deployment, there is a significant gap. This training course bridges that gap: you will learn how these models work, how to customise them for your needs, and how to deploy them in real environments — from API integration to fine-tuning, through to RAG architectures.

Whether you are a developer, data scientist or IT architect, this training course will give you the technical tools to get the most out of LLMs in your projects.

Format

Remote (recorded sessions). It is possible to customise the training course for a private group. Contact us for more information.

GOOD TO KNOW

This training course includes numerous exercises (60% practical). Each participant will work with real LLM tools and APIs. You will build real use cases: chatbot, document summariser, domain-specific assistant. This training course is regularly updated to keep pace with the rapid developments in the field.

Objectives of the Generative AI and LLMs Training Course

By the end of this training course, each participant will be able to:

Understand how LLMs work (architecture, training, limitations)
Choose the right model for a given use case (GPT, Claude, Mistral, open-source)
Integrate a model via API (OpenAI, Anthropic, HuggingFace)
Build a RAG (Retrieval-Augmented Generation) pipeline
Fine-tune a model on custom data
Deploy an LLM application in a real environment
Evaluate model performance and manage costs

Prerequisites for this Generative AI and LLMs Training Course

Python programming experience recommended
Basic understanding of machine learning concepts
Familiarity with APIs (REST)
Because each participant is unique, a personalised interview with our expert allows us to design a training programme perfectly aligned with their objectives, level and professional challenges.

Target Audience

This training course is designed for :

Python developers
Data scientists and ML engineers
IT architects wishing to integrate LLMs into their systems
Technical profiles working on AI projects

Detailed Programme of the Generative AI and LLMs Training Course

How LLMs Work

How LLMs work (transformers, embeddings, tokens, generation models). Why do they produce what they produce? A simplified introduction.

Overview of Major Models

GPT-5, Claude, LLaMA, Mistral, Mixtral, Phi… how to choose based on your needs (cost, performance, privacy, open source, etc.). Comparative demos.

Prompt Engineering and RAG

Prompt engineering techniques: roles, contexts, loops, logical chains. Using memory, RAG (Retrieval-Augmented Generation) and agents.

Integrations and APIs

Using OpenAI, HuggingFace, Anthropic APIs. Creating web assistants, integration with Notion, Slack, CRMs, etc. Low-code or custom frameworks.

Deployment Use Cases

Deployment examples: internal chatbot, business copilot, meeting summarisation, legal or HR summary engine. Local or cloud deployment (serverless, etc.).

Governance, Security and Responsible AI

Governance, data security, hallucinations, output control, auditability. Responsible use cases and error management.

Why This Training Stands Out

What sets this training apart:

It demystifies LLMs without oversimplifying them, with a balance between theory and practice.
It goes beyond prompts to explore advanced techniques such as RAG, agents and fine-tuning.
Real, immediately applicable use cases.