Writing

Blog

Technical writing on AI engineering, edge deployment, and production ML.

How I Deployed YOLOv8 at 30ms on Edge Hardware (No GPU Required)

A step-by-step technical guide to deploying YOLOv8 on a Rockchip RV1126 using RKNN INT8 quantization — achieving sub-30ms inference without any GPU.

8 min readJune 20, 2025

Read article

New

Agentic AI

Building Agentic Web Scrapers That Scale to Millions of Records

How to architect a production-grade agentic scraping system using LangChain and Playwright — with fault tolerance, proxy rotation, and LLM-based semantic extraction that survives site redesigns.

10 min readJune 25, 2025

Read article

Coming Soon

LLMs

What I Learned Evaluating LLMs at Turing

Behind the scenes of LLM red-teaming: how to systematically find failure modes in frontier models and structure feedback that actually moves the needle.

4 min read