Physical AI · Robotics software | Imitation-learning data · Simulation · Sim-to-Real | Python · C++ · ROS 2 · MuJoCo
M.S. in Advanced Device Technology (optical R&D) → web planning → full-stack web team lead → robot software.
I connect simulation data, learned policies and real robots, and report each result with the conditions it was measured under.
🎓 Physical AI program (DAPIER Cohort 1), Dongguk University · 656 hours · Jul 6–Nov 4, 2026 · completed
🧹 SWEEPICK (team of 4): low-cost mobile dual-arm robot that clears floor objects. I led SIM data and domain randomization, Sim-to-Real integration and the ROS 2 base↔arm hand-off, and co-developed the ACT policy. First unattended end-to-end real run on Nov 1, 2026; real grasps 7/10 · 8/10 · 7/10 across three objects; SIM closed loop 132/143.
🚗 deepThinkCar: stop gates and candidate-model evaluation; steering MAE 14.93° → 4.93° on the same split, held back from the car because the evaluation range was narrow.
⏱️ SyncGuard: time-alignment checks before training; valid alignment 33.6% → 98.2% and p95 skew 46.7 → 3.3 ms on synthetic jitter/drop data.
🧭 ROS 2 practice: URDF, TF, SLAM and Nav2 on Jazzy, with Humble → Jazzy migration diagnostics.
🏗️ VERA: interior/construction SCM platform built with coding agents in two weeks; LLM APIs with rule-based fallbacks and a Vitest/Playwright QA pipeline.
⚽ soccerhelper: web/mobile MVP for amateur football teams (Next.js · Expo · Supabase).
💼 Earlier work: full-stack web team lead (React/Next.js, Supabase, Playwright automation), freelance full-stack (NestJS, payments and webhooks, GitHub Actions, Docker/EC2), optical transceiver R&D.
| Topic | Details |
|---|---|
| 📍 | Korea · completed the Physical AI program on Nov 4, 2026 · looking for robotics software roles in imitation learning, simulation, Sim-to-Real and robot integration |
| 🔧 | Hands-on: Python, C++, ROS 2 (topics, TF, URDF/RViz), Nav2 basics, MuJoCo, Isaac Sim, RoboTwin, LeRobot / ACT, PyTorch, OpenCV, Linux |
| 🧪 | Recent work: dual-arm ACT data and evaluation, Sim-to-Real hand-off on SO-101 arms, ROS 2 base↔arm interface |
| 🤖 | AI-native: coding agents (Claude Code, Codex) driven by specs, tests and acceptance checks; LLM features with rule-based fallbacks; personal automation agents |
| 📚 | Start here: portfolio · SWEEPICK · mini projects & practice |
Windows bug fixes in widely used Python projects. I reproduce each bug on Korean Windows (cp949) and add a regression test that fails before the fix.
| Project | Change | Status |
|---|---|---|
| jupytext | Use UTF-8 for the temporary files exchanged with marimo |  |
| Panel | Read and write user files as UTF-8 |  |
| commitizen | Explicit encodings in cz commit --edit and cz init |
 |
| huggingface_hub | Read --filter-from files as UTF-8 |
 |
| Locust | Read locustfiles as UTF-8 before sending them to workers |  |
| python-semantic-release | Read the previous changelog as UTF-8 |  |
| Salt | Fix network.connect always failing with proto=udp |
 |
| xonsh | Read the RC file, xontrib sources and the stash log as UTF-8 |  |
| Apprise | Read Discord, Slack, Telegram and Workflows templates as UTF-8 |  |
| pipenv | Keep the downloaded requirements file for pipenv install -r <url> |
 |
| OpenJarvis | Format digest dates without glibc-only strftime flags |
 |
