A conceptual diagram of a RAG pipeline with document ingestion, vector store, retriever, re-ranker, and LLM generator stages.

Building a Production-Grade RAG Pipeline: A Hands-On Portfolio Project That Signals Real Systems Skill

Move beyond the generic FAISS + LangChain + OpenAI tutorial. This guide walks you through building a multi-stage RAG pipeline with hybrid retrieval, cross-encoder re-ranking, and automated evaluation — the kind of project that signals real systems skill on a CV.

September 9, 2026 · 12 min · 2549 words · martinuke0
A visualization of vector embeddings organized in an HNSW graph structure with clustered partitions

Building a Pure-Python HNSW Index with IVF Clustering and Brute-Force Rescoring

A hands-on guide to building a pure-Python HNSW index with IVF clustering and brute-force rescoring. Learn how approximate vector similarity search works under the hood and create a portfolio project that signals deep systems expertise to hiring managers.

September 9, 2026 · 13 min · 2668 words · martinuke0
A visualization of an HNSW graph structure with layered nodes and edges

Build an HNSW Vector Index from Scratch in Python for RAG

Build an HNSW graph vector index from scratch in pure Python and integrate it into a RAG pipeline. This hands-on guide covers the full implementation, testing, and a roadmap to production-grade features.

September 8, 2026 · 13 min · 2737 words · martinuke0
A code editor showing a Python implementation of a transformer attention block with mathematical notation in the background.

Build a Transformer Self-Attention Block from Scratch in Pure Python

A hands-on guide to implementing a transformer self-attention block from scratch in pure Python, covering rotary positional embeddings, causal masking, and grouped-query attention — with real, runnable code and a roadmap to production-grade extensions.

September 8, 2026 · 14 min · 2776 words · martinuke0
Diagram of a paged KV cache with blocks, block tables, and a prefix-sharing radix tree.

Build a Paged KV Cache Manager From Scratch: A Portfolio Project That Signals Real Systems Skill

Step-by-step build of a real, runnable paged KV cache manager in Python: blocks, block tables, prefix sharing via a radix tree, copy-on-write for beam search, plus a roadmap to senior-level extensions.

September 7, 2026 · 13 min · 2661 words · martinuke0
Feedback