Kiyoung So

I build products 0→1, solo —
hardware → WASM → cloud.

Full-Stack & AI Engineer · 11 years. I own every layer — from the metal (C++/WASM) to the cloud — and ship it to production myself.

ssogi@ssogi.com Live demo ↓
What I do

Centered on AI & agents — standing on deep full-stack, platform, and real-time CV/ML experience.

AI & agent tooling
Multi-agent orchestration, LLM-driven dev platforms, local-first AI infra.
Full-stack product
React · React Native · Next · Node · NestJS · FastAPI · Spring — 0→1 to production.
Platform & infra
AWS, Docker, CI/CD, real-time pipelines, licensing, zero-downtime deploys.
Real-time CV/ML
Gaze tracking, C/WASM inference, 6-DOF pose, fixation detection — live below.
Live demo

The deepest layer, proving the rest: real-time CV/ML compiled to WebAssembly, running on your own webcam. Read the passage for 12 seconds and watch your gaze path replay. No install, nothing uploaded.

Most people think they read in smooth lines. In fact your eyes move in quick jumps — saccades — pausing only at brief fixations a few times a second, and you are effectively blind in between. What feels like a continuous sentence is stitched together from a handful of sharp glimpses. This demo just recorded where yours landed, and in what order. Watch your own reading path replay.

Webcam eye-tracking, compiled to WebAssembly — runs entirely on your device.
~30 fps · webcam-bound MediaPipe + TFLite → C/WASM SharedArrayBuffer zero-copy 6-DOF pose · 1€ filter · I-VT/I-DT

Also running in production for real clients.

Selected work · all solo-shipped

R_workstation — multi-agent dev platform

AI / agents
solo · daily driver for 3 devs · local-first
  • Spawn & orchestrate local multi-agent (Claude Code) sessions from a phone
  • Hono + socket.io + SQLite backend · React PWA
  • TOTP auth · Tailscale Funnel · child-process lifecycle management
Local-first: zero data leaves the machine.

Commercial eye-tracking analytics platform

full-stack + infra
end-to-end owner · led a 4-person team · built the core myself
  • Hardware→browser bridge: Tobii C++ SDK → Node native addon → Electron → WebSocket → React
  • HTML5 Canvas gaze analytics (replay, heatmaps, fixations, scanpath, AOI) + behavioral-scoring ML
  • Full AWS infra: CI/CD, Redis, OAuth, monitoring, zero-downtime deploys
Led the team while architecting and building the core end-to-end.

Browser webcam gaze tracking (CR_wasm)

real-time CV/ML
solo · ~30 fps in-browser · live in the demo above
  • Ported MediaPipe + TFLite to C/WASM (Emscripten + Bazel, XNNPACK SIMD), SharedArrayBuffer zero-copy
  • 6-DOF head pose (solvePnP), 1€ filter, I-VT / I-DT fixation detection
  • HMAC + ECDSA licensing · S3 / CloudFront distribution
Owned every layer: CV math → WASM build chain → browser runtime → cloud.

Tobii 5L native integration

hardware → cloud
solo · full system boundary
  • C++ SDK → Node native addon → Electron, including the full build chain
  • IPC / WebSocket real-time streaming, live visualization, data analysis
  • Cloud sync + licensing
Designed the entire hardware → cloud boundary alone.
How I work

Remote-first and async (KST, comfortable with night overlap), location-independent. Open to Founding / Staff Engineer roles and contract / EOR engagements with teams that move on results.

My edge isn't breadth for its own sake — it's breadth that stands on real depth in every layer. If you're building AI/agent tooling, full-stack products, or real-time/edge systems and want someone who can own the whole thing — let's talk.

ssogi@ssogi.com