Machine-Learning

Illustration of a Python neural network pipeline

From‑Scratch Speculative Decoding Engine in Pure Python

A hands‑on guide to building a from‑scratch speculative decoding engine in pure Python, with draft‑then‑verify sampling, temperature, top‑k and nucleus (top‑p) sampling, all using only numpy. Perfect for a CV‑boosting side project.

A developer's workspace with code and retrieval diagrams.

Build a ColBERT‑Style Late‑Interaction Retriever in Pure Python

Learn how to construct a fast, vector‑less late‑interaction retriever and inverted index using only standard Python, and why it impresses hiring managers.

A clean visualization of probability distributions after different decoding strategies

From Scratch Decoding: Building a Pure-Python Sampler for Transformer Logits

A hands-on guide to building a pure-Python sampler for transformer logits, covering temperature scaling, top-k, top-p, and typical-p decoding from scratch.

Build an Attention Block from Scratch: A Portfolio Project for Systems Engineers

Learn to implement a transformer attention block from scratch in Python, package it as a service, and extend it with production-grade features.

A diagram of the embedding adapter architecture.

Building a Self-Supervised Embedding Adapter for Arbitrary Vectors

Learn to build a self-supervised adapter that maps any embedding to a similarity-preserving space, with production-ready PyTorch code.