We’ll cover how to break down complex AI problems, select the right tools from the GenAI ecosystem, and master Databricks-specific technologies: Vector Search for semantic retrieval, Model Serving for real-time deployment, MLflow for managing the model lifecycle, and Unity Catalog for data governance — ultimately enabling you to build and deploy RAG applications and LLM chains in production.
For this course, I chose to work with the Databricks Free Edition, a free version accessible to everyone. While it doesn’t include features still in beta, I keep it regularly updated. The course blends theoretical presentations with hands-on workshops illustrating key concepts, all grouped together in a GitHub project.
This course is aimed at developers — whether software engineers, data scientists, or data engineers — who have already built POCs using frameworks such as LlamaIndex, LangChain, or CrewAI. If you have a working knowledge of Python and SQL and want to master every step of taking your work to production on Databricks — then validate those skills through certification — this course is for you.
