A visualization of a KV cache data structure with key and value tensors being incrementally appended during autoregressive LLM decoding.

Building a Pure Python Incremental KV Cache for Efficient Long-Context LLM Inference

Build a production-grade incremental KV cache from scratch in pure Python. This guide covers architecture, implementation, testing, and a roadmap to production-flavored features that signal real systems skill to hiring managers.

September 13, 2026 · 14 min · 2877 words · martinuke0
A visual representation of a user safety scoring pipeline processing content through multiple detection layers.

User Safety: safe — A Hands-On Build Guide for Your Portfolio

A complete build guide for a User Safety scoring engine — covering architecture, step-by-step implementation with real code, testing strategies, and a senior-level extension roadmap.

September 11, 2026 · 11 min · 2219 words · martinuke0
A dashboard showing flagged user content

Building a Real-Time User Safety Pipeline: A Portfolio Project

A hands-on guide to building a production-flavored user safety service that ingests, moderates, and logs user content in real time.

September 10, 2026 · 9 min · 1723 words · martinuke0
Conceptual diagram of a dynamic context buffer

Dynamic Context Buffer with Learned Relevance Predictor

This post walks you through implementing a token‑aware context buffer that learns relevance and prunes low‑value tokens to fit a target window.

September 10, 2026 · 7 min · 1312 words · martinuke0
Diagram of a user safety event pipeline with Kafka, PostgreSQL, and Go services

User Safety: safe – A Hands-On Build Guide for a Portfolio CV Project

A complete, runnable project that demonstrates distributed event-driven design, backend engineering, and observability skills hiring managers look for in senior and staff-level engineers.

September 9, 2026 · 11 min · 2199 words · martinuke0
Feedback