Applied AI & LLM Engineering with Python Training in Kraków, Poland

This training provides a comprehensive foundation in Applied AI and LLM Engineering using Python. Participants will explore the principles of artificial intelligence, machine learning, and large language models, focusing on practical implementation and deployment. The course covers essential Python libraries, model development, fine-tuning, and integration of LLMs into real-world applications. Through a blend of theory and hands-on exercises, learners will gain the skills needed to build and manage AI-driven solutions.

Introduction to Applied AI and Python Ecosystem

• Overview of artificial intelligence and its applications
• Setting up the Python environment for AI development
• Key libraries: NumPy, Pandas, Scikit-learn, and Transformers
• Data preprocessing and feature engineering

Hands-on exercises

Machine Learning Fundamentals

• Supervised and unsupervised learning algorithms
• Model selection, training, and validation
• Evaluation metrics and cross-validation techniques
• Handling overfitting and underfitting

Hands-on exercises

Deep Learning with Python

• Neural network architecture and activation functions
• Building models with TensorFlow and PyTorch
• Training deep networks and backpropagation
• Regularization and optimization strategies

Hands-on exercises

Introduction to Large Language Models

• Transformer architecture and attention mechanisms
• Pre-trained models and transfer learning
• Working with Hugging Face Transformers library
• Tokenization and model inference

Hands-on exercises

Prompt Engineering and Fine-Tuning

• Designing effective prompts for LLMs
• Fine-tuning pre-trained models on custom datasets
• Parameter-efficient fine-tuning techniques
• Evaluating and improving model responses

Hands-on exercises

Building AI-Powered Applications

• Integrating LLMs into web applications
• Developing chatbots and conversational agents
• Using APIs for model deployment
• Handling context and memory in applications

Hands-on exercises

Model Deployment and Scaling

• Containerizing AI models with Docker
• Deploying models on cloud platforms
• Monitoring and logging in production
• Scaling inference with load balancing

Hands-on exercises

Ethics, Bias, and Responsible AI

• Identifying and mitigating bias in AI models
• Ensuring fairness and transparency
• Privacy considerations and data governance
• Compliance with AI regulations

Hands-on exercises

Advanced Topics and Future Trends

• Multimodal AI and vision-language models
• Retrieval augmented generation (RAG)
• Emerging trends in LLM research
• Building custom tooling and pipelines

Hands-on exercises