Everything is Data Engineering. Even AI.
Modern AI isn’t magic. It’s infrastructure.And like all good infrastructure, it needs solid engineering.
This track gives you the real foundations behind GenAI, the kind that matter for Data Engineers.You’ll start with embeddings, understand how vector search works, and then build actual systems: semantic search apps, local RAG pipelines, and fully self-hosted agents that respond to real user input. No black boxes. No cloud dependencies. No hype.
You’ll work with the tools that power real-world GenAI systems, Python, FastAPI, Qdrant, Elasticsearch, Streamlit, Ollama, Slack, n8n and build everything step by step. From chunking documents and calculating similarity scores, to building MCP servers and triggering fallback logic with Jira tickets.
By the end, you won’t just “know” how GenAI works. You’ll have built the full stack yourself, local, portable, and production-ready.
The first course on embeddings is already live. The next projects, semantic search and RAG, are fully developed and will be released soon.
This is AI for engineers who ship.
And it’s all just Data Engineering.
Everything in this track:
Pricing
The AI Engineering track is included in our Data Engineering Academy
