Sangwon Ji

I'm an AI engineer who builds multi-agent systems that check their own work

Orchestration, retrieval over knowledge graphs and evals, shipped as services with tests, traces and one-command deploys.

See my work
Based in
Waterloo, ON
Studying at
University of Waterloo
Working on
Growing The Sovereign's learning pipeline and its review queueHardening Catchbunny's MCP endpoint for Claude Code and Codex

Experience

Full resume
  1. Qorsa

    Machine Learning Engineer (AI Engineering)

    Jan 2026 – Dec 2026

    Made report-writing agents 6× faster on 20× fewer tokens

    • 83k → 4ktokens per report section
    • 77s → 12sto write each section
    • ~25ktokens saved per section, with tools run in code

    Python, FastAPI, Pydantic, Dgraph, Langfuse

  2. SK Networks & ENCO

    AI Full-Stack Apprentice

    Feb 2025 – Aug 2025

    Shipped real-time AI apps to AWS

    • <1slive data over WebSocket and SSE
    • 0manual deploy steps, with CI/CD on AWS

    FastAPI, Redis, Next.js, OpenSearch, AWS

Selected work

3 of 5 projects

Catchbunny

Solo projectPython, asyncio, Playwright, FastAPI, SQLite, MCP, React

Browser testers that prove a bug before they report it

  • 9/9planted bugs found
  • 78 → 28steps to reproduce, after shortening
  • 4.6×faster with 8 testers than 1

Measured on the bundled benchmark, no AI model

catchbunny / example run
  • step
  • detector fired
  • happened again
  • did not repeat
Example run, redrawn from Catchbunny's console

The Sovereign

Solo projectPython, Pydantic AI, FastAPI, ArcadeDB, MCP, Ollama, Claude API, Docker

A research lab that learns every night and proves it on an exam

  • 41 → 55held-out exam score after its research
  • 1,010sourced facts from 47 pages in one night
  • 9×faster fact extraction on a local model, same quality

From the lab's own records

the-sovereign / example run
  • task
  • report
  • tool call
  • facts stored
  • dropped
Example run, redrawn from The Sovereign's agent team

StudyNotch

Solo projectSwift, SwiftPM, Claude Code

Ask Claude about what you're reading, right from the MacBook notch

  • ~4.4klines of Swift
  • 60+built-in self-test checks
  • 0servers, it runs fully on your Mac

All projects

Hiring an AI engineer? Let's talk

Open to AI engineering internships and roles. Email is the fastest way to reach me.