RuffLogix

Research‑Driven
Software Engineering

Building intelligent systems, experimental software,
and high‑performance digital experiences.

About

Software engineer and AI researcher based in Bangkok. Currently full-time at Khui AI on LLM training, fine-tuning, and deployment, alongside an AI engineering apprenticeship at KBTG. Previously at Agoda — bridging LLMs and Temporal.io through MCP — plus LINE MAN Wongnai, AIMET, and Looloo Technology, across federated learning, speech AI, backend systems, and smart contracts.

Computer Engineering student at Chulalongkorn University. Super AI Engineer Season 5 · iGEM 2024 Silver · TOI Thailand 2020/2021.

Full background

Focus Areas

AI Systems Systems Programming Software Architecture Experimental Interfaces Research Engineering High-Performance Computing

Selected Work

All projects
Web Development 2026

RuffBlitz School — Block-Based LMS

A learning management platform where courses are assembled from composable "blocks" — Lego-like pieces (text, video, quizzes, code, and more) that instructors snap together to build lessons. Aimed at flexible, hands-on course authoring.

NextTypeScriptLMSEdTech
Web Development 2026

Online Judge / Grader for LMS

A self-hostable online judge embedded in the RuffBlitz LMS for programming and algorithms courses. Compiles and runs Python/C/C++ through a sandboxed execution engine (Judge0 → isolate) driven by horizontally-scaled judge workers, with role-based access (admin/staff/student), group-gated problem visibility, ICPC/IOI-style contests with scoreboard freeze, subtasks and testlib checkers. Built on Next.js + Elysia (Bun), PostgreSQL/Drizzle, and Redis/BullMQ.

ElysiaBunNextPostgreSQLRedisJudge0
AI / Machine Learning 2026

Urine Color Classifier

A lightweight ordinal image classifier that grades urine color on a 5-point scale (Clear → Very Dark) as a coarse hydration proxy, built for CPU inference. Treats the ordered classes as ordinal regression (class-weighted CE + Squared-EMD loss), with color-preserving augmentation, effective-number class balancing, and a held-out + 5-fold stratified protocol. Reaches QWK 0.963 on the test set with 100% adjacent accuracy — every error is off-by-one — while a trivial color+GBM baseline matches ~98% of it, making the efficiency case for tiny deployment. Delivered as a LINE chatbot via the LINE SDK and Messaging API, so users get a hydration reading by sending a photo in chat. Not a diagnostic tool.

PyTorchComputer VisionOrdinal RegressionCNNLINE

Research Philosophy

Precision

Every abstraction earns its place. Every line justifies itself.

Scalability

Systems designed to bend without breaking under real-world pressure.

Exploration

The frontier matters. Running experiments where answers are unknown.

Craftsmanship

Software as a discipline — executed with the rigour of a craft.

" The best systems feel inevitable in hindsight —
rigorous craft disguised as simplicity.

Writing

All posts