Course Outline
Curriculum Overview Training Proposal
Day 1 - AI and Python Fundamentals for Data Workflows
• Overview of the current AI and machine learning landscape
• The impact of AI on modern data engineering practices
• Refresher on Python fundamentals for AI contexts
• Data manipulation using pandas and NumPy
• Introduction to API interactions and JSON data management
• Practical exercise: Loading and transforming datasets
Day 2 - Machine Learning Essentials for Practitioners
• Concepts of supervised and unsupervised learning
• Techniques for feature engineering and data preparation
• Fundamentals of model training with scikit-learn
• Assessing model performance and evaluation metrics
• Introduction to model deployment strategies
• Hands-on session: Building a basic predictive model
Day 3 - LLM Fundamentals and Prompt Engineering
• Understanding the operational mechanics of large language models
• Tokenisation, context windows, and inherent limitations
• Core principles and techniques for prompt design
• Applying zero-shot and few-shot prompting methods
• Strategies for prompt evaluation and iterative improvement
• Practical exercises in prompt engineering
Day 4 - Developing AI Applications with LLMs
• Utilising LLM APIs within Python environments
• Managing structured outputs and function calling
• Constructing chat-based and task-oriented applications
• Introduction to Retrieval Augmented Generation (RAG)
• Integrating LLMs with external data sources
• Mini project: Creating a basic AI assistant
Day 5 - Deploying AI Solutions to Production
• Architecting scalable AI workflows
• Integrating AI components into data pipelines
• Monitoring and optimising model performance
• Strategies for cost management and efficient API usage
• Addressing security and responsible AI considerations
• Final project: Constructing a complete end-to-end AI solution
Testimonials (2)
The trainer was very available to answer all te kind of question I did
Caterina - Stamtech
Course - Developing APIs with Python and FastAPI
Trainer develops training based on participant's pace
