Practical OpenSource AI

This course provides a hands-on introduction to Artificial Intelligence with a strong focus on Linux-based development environments and OpenSource tooling. Participants gain practical experience implementing and deploying open-source Large Language Models on Linux systems, with emphasis on production use, data security, and system integration.

Introduction

• AI foundations on Linux
• System architectures and development environments
• Python fundamentals for AI

OpenSource LLMs

• LLM architecture and evaluation
• Local deployment and production setup
• Privacy, compliance, and security considerations

LLM Integration & Safeguards

• Prompt engineering and input validation
• RAG systems (Retrieval-Augmented Generation)
• Tool calling, agents, and secure API integration

Classical Neural Networks

• Multilayer Perceptron
• Convolutional and Recurrent networks

TensorFlow / Keras

• Model definition, training, and evaluation
• Transfer learning and LLM integration

Applied Machine Learning

• Data preparation and prediction tasks
• Hybrid ML + LLM systems

Operations

• Performance scaling and failure modes
• Monitoring and maintenance
• Use case discussion

Target audience: Engineers, developers, and technical professionals responsible for designing, building, or evaluating AI systems on Linux.

Prerequisites: IT background with general Linux skills (command-line experience). Basic Python knowledge required; additional programming experience recommended.

Materials: Course materials plus “Tutorial: Practical Artificial Intelligence on Linux” by Jasper Nuyens.