Skip to content

Full-stack engineer building AI agents and knowledge graphs, from research to commercial release

I am a founder, product owner, and full-stack builder focused on turning complex, unstructured real-world problems into scalable, production-grade software platforms.

As Founder and CEO of Intergalactic, I led the end-to-end development of a high-complexity SaaS platform spanning ERP, CRM, payments and operations. I personally designed the system architecture and wrote more than a million lines of production code, while owning product strategy, UX/UI, engineering execution, fundraising and company operations.

The platform scaled to more than 10,000 users, generated over $770K in GMV, and secured more than $1M in funding across venture capital, government R&D programmes and guarantee-backed financing.

I have collaborated with global organisations including Google, Microsoft, JP Morgan and UK-based accelerators, and have presented products at international demo days and major technology expos.

Open to new opportunities Seoul, South Korea

Now

I am building an ontology-driven coding agent on the Coding Agent team at Wrtn Technologies, and applying the knowledge-graph and retrieval design validated in Consilience to it.

Youngtak Jo presenting on stage
Youngtak Jo presenting on stage, holding a microphone
Youngtak Jo pitching, seated at a laptop
First Hamseongsori IR demo day — Work Together Foundation · YBI · Google.org, 2022 High Flyer investment demo day — JPMorgan Chase · Work Together Foundation · YBI, 2024 Fundraising accelerator pitch — Seoul Youth Startup Academy · Smilegate Investment, 2024

Highlights

Selected work

Projects

A selection of projects and the results each one produced.

Apr 2026 – Present

Consilience

The world's first general-purpose ontology OS — it builds a knowledge graph from markdown documents automatically, and an agent reasons over that graph

78.80% SWE-bench Verified resolve rate, all 500 tasks

Ontology AI Agent Research Platform

Wrtn Technologies · Independent — solo product

Feb 2026 – Mar 2026

Rxly.ai

An AI consultation assistant that analyses the consultation in real time and does the charting for the clinician — a finalist at Anthropic's hackathon

230 / 13,000 Anthropic Opus 4.6 hackathon finalist — the only Korean finalist

AI Agent Research Platform

Freelance and personal projects

Nov 2025 – Dec 2025

Xhadow

A pronunciation coach built on AI voice cloning and in-browser acoustic analysis that corrects articulation instead of reporting a score

422ms → 23ms time-axis alignment, 18× faster with zero inversion error

AI Agent

Freelance and personal projects

Aug 2022 – Sep 2025

LOCL

An all-in-one operations platform for class and studio businesses — booking, payments, settlement, scheduling, CRM and marketing in one workflow

10,000+ cumulative users

Platform

Intergalactic Inc.

Feb 2025 – Jul 2025

Vime

An online meetup simulator in which several AI personas take part at once and adapt their responses to the conversation

3 variables — agenda, personas, layout — generate any scenario

AI Agent Platform

Intergalactic Inc.

Jan 2019 – Oct 2019

INTRO — a piano teaching instrument

Hardware that turns piano practice into a rhythm game, built on MIDI control and an embedded system

2 single-board computers driving a light-diffusing acrylic LED interface

Research

Personal project

View all projects

Experience

The organisations I have worked in and what each role produced.

Period Organisation Role Projects
Seoul Wrtn Technologies Current

Agent Developer, Coding Agent Team

  • Lead ontology-driven AI agent development on the Coding Agent team.
  • Continue to develop Consilience and apply its knowledge-graph code intelligence to the team's product.
  • (to be filled in — specific outcomes and metrics at Wrtn)
Consilience
Seoul Independent — solo product Ongoing

Solo founder and engineer — Consilience

  • Built the world's first general-purpose ontology OS alone, from research through to commercial release: roughly 468,000 hand-written lines, seven languages, signed macOS and Windows builds. Solo · shipped commercially
  • Measured all 500 SWE-bench Verified tasks on the official harness, and isolated the scaffold's own contribution at 54% → 76% with the model and a 50-task set held fixed. 78.80%
  • Ranked first on the official DP-Bench leaderboard for table structure recognition, above Upstage, AWS, LlamaParse, Microsoft and Google. TEDS-S 98.11
Consilience
Seoul Freelance and personal projects

Full-stack engineer — Anthropic and OpenAI hackathons

  • Selected for the final 230 of roughly 13,000 applicants in Anthropic's Built with Opus 4.6 Claude Code hackathon, and the only Korean participant. 230 of 13,000
  • Implemented FFT, formant extraction and voiced/unvoiced detection in the browser, holding phoneme-level error under 10 Hz. ±10Hz
  • Made time-axis alignment 18× faster with a hybrid DTW, with inversion error held at zero. 422ms → 23ms
Rxly.ai Xhadow
Seoul Intergalactic Inc.

Founder and CEO · Strategy team

  • Raised venture capital, central-government R&D grants, public support funding and guarantee-backed financing. ₩1.4B+ raised
  • Graduated 23rd of 100 companies in cohort 5 of the Changgu programme run by Google and the Ministry of SMEs and Startups. 23rd of 100
  • Designed and built the whole surface — customer app, admin back office and CMS: 1,390 dynamic screens across 1,042,300 lines. 10,000+ users · ₩100M+ GMV
LOCL Vime
Seoul Hansol PNS

Senior Researcher, Standard Software Research, ITS Division

  • Proposed and built a setup that put responsive web, iOS and Android in one monorepo with Expo and Next.js, in order to cut development and maintenance cost.
  • Wrote and published the standard library and its guidelines, and trained the developers who used it.
MES Cross-platform Standard Framework
Seoul Intro

Software outsourcing and in-house product development

  • A property transaction management platform (client work)
  • Handset identification and accessory locator software (client work)
  • A personality-quiz marketing platform (in-house)
Seoul Sewon Atos

Researcher, R&D Institute

  • Trained a CNN on 32,474 crawled images with a single GPU to classify apparel categories automatically. 90%+ accuracy
  • Wrote the vector-similarity data cleansing and post-processing pipeline myself.
  • Handled the EWERP research and development that moved a Delphi-based ERP onto a cross-platform web stack.
Garment Type Classification Vision AI

One-page résumé Full CV Research and benchmarks Press coverage