RAG & Vector Search in Production

Chunking, embeddings, hybrid search, re-ranking and evaluation — build a retrieval layer that holds up under real queries.

⏱ 6 weeks🎚 Intermediate🧩 2 projects · Certificate🖥 Any device · our GPUs

Apply for this course Where this leads

Draft syllabus. Timeline and topics are indicative and being finalised with the teaching team — the shape is right, the week-by-week detail may shift.

🎯 Who it's for

Engineers who can already make a basic LLM call and want retrieval that actually works on messy data.

✅ Prerequisites

Python
Comfort calling an LLM API
A rough idea of what an embedding is (we cover the rest)
LLM Application Engineering helps but isn't required

Topics covered

Chunking strategies and trade-offs
Embeddings and vector stores
Hybrid keyword + vector search

Re-ranking and metadata filtering
Building a retrieval evaluation set
Citations and “I don't know” handling

Expected completion timeline

6 weeks part-time at 8–12 hours per week ≈ 1.4 months. Self-paced learners can go faster; the live cohort keeps this pace.

Wk 1–2

Index and retrieve

You produce: A working RAG pipeline over a supplied corpus.

Wk 3–4

Better retrieval

You produce: Hybrid search plus re-ranking, measured against a labelled set.

Wk 5–6

Evaluation and hardening

You produce: A retrieval evaluation report and a documented service.

🧭 Where this fits

Part of the LLM / Generative-AI Engineer path. See the career & salary map for the full path, the expected pay by region, and the total cost.

💳 Delivery & fees

Available in all four delivery formats. Fees vary by format and are confirmed on your advisor call; instalments available. [Add the fee and the next cohort date here.]

Add this to your plan

Book a call and we'll place this course in a full path toward the role you want.

Talk to an advisor