Skip to main content

RuffLogix

Research‑Driven
Software Engineering

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

About

Independent software engineer and AI researcher based in Bangkok. Currently at KBTG, Agoda, and Khui AI, building LLM-powered systems with MCP and Temporal.io. Formerly at LINE MAN Wongnai, 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 SystemsSystems ProgrammingSoftware ArchitectureExperimental InterfacesResearch EngineeringHigh-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