Hands-on Build Guide: Tiled Self-Attention Kernel with Online Softmax in Pure NumPy
A step‑by‑step NumPy implementation of tiled soft‑max attention, mirroring FlashAttention’s efficiency, perfect for a CV‑boosting side project.
Hands‑On Build Guide: LoRA‑Augmented Transformer Attention Block in Pure Python
A step‑by‑step guide to implementing a LoRA‑modulated attention block in pure Python, complete with runnable code, testing, and a roadmap to production‑grade extensions.
User Safety: A Hands‑On Build Guide for a Portfolio CV Project
A Go‑based CLI that validates and sanitises arbitrary user input against JSON schemas, logs every decision, and ships as a static binary for instant portfolio deployment.
Speculative Decoding with Parallel Verification: A Hands-On Build Guide
A practical, end-to-end guide to building a speculative decoding prototype with parallel candidate verification, complete with runnable code and deployment tips.
Minimal LoRA Fine-Tuning and Adapter Inference Engine in Pure Python
Build a compact LoRA engine from scratch, demonstrating systems skills that catch hiring managers’ eyes.