Senior Specialist Manager · Open-source contributor · AI agent & data systems builder
I turn architectural intent into reliable, agent-assisted systems built for Digital Transformation (DX) and AI Transformation (AX). My work connects AI agent orchestration with governed, virtualized enterprise data—creating a trusted semantic layer across fragmented sources without unnecessary data duplication. I combine data virtualization, data governance, metadata and lineage, data quality, access control, big-data infrastructure, and cloud-native architecture to move promising ideas into source-verifiable production systems designed for scale, observability, and trust. As an OPDC (Open Platform Developer Community) Leader, I also help developers learn and grow through open-platform collaboration, open-source contribution, eGovFrame programs, technical seminars, and community support.
- Agent-native engineering — MCP servers, orchestration harnesses, and governed workflows that let humans express business intent while agents plan and implement safely, with traceability and human oversight.
- DX, eGovFrame & open-platform community — advancing modernization through OPDC leadership, open-source contribution, developer enablement, data virtualization, and semantic integration across fragmented enterprise and public-sector systems.
- Governed AX & data platforms — grounding generative AI in cataloged, lineage-aware, quality-controlled data, with metadata, policy, and access controls built for production-grade analytics and AI.
| Project | What it does |
|---|---|
| egovframe-scaffold-mcp | Proof-of-concept MCP server for scaffolding eGovFrame projects. |
| iroum-ax | AI automation platform for public-institution evaluations — HWP ingestion with VLM/RAG gap analysis (Go · Python · Next.js). |
| iroum-cms | eGovFrame 5.0-based CMS for public institutions with AI-powered policy matching (Spring Boot · Vue 3). |
| ai-stock-picker | AI stock/ETF recommender using Claude news-sentiment analysis, real-time prices, and backtesting (FastAPI · React). |
| lotto | Statistical recommendation CLI and web dashboard built with Python. |
- Improving information architecture, links, source tables, and developer guidance in eGovFramework/egovframe-docs.
- Contributing security, download-correctness, performance, and maintainability fixes to eGovFramework/egovframe-common-components.
- Exploring agent-native public-sector development through MCP-based eGovFrame scaffolding.
- Leader, OPDC (Open Platform Developer Community) · 2024–present — supporting open-platform quality and productivity through open-source development, eGovFrame contribution, technical seminars, and developer community programs.
- Recognition of Contribution, e-Government Standard Framework · 2022–2025
- 1st Place, Cisco FY21 DevNet Innovators Hackathon
- Patent application (2025) — System and Method for Providing Visualization-Based Source Information Using Large Language Models (LLMs)
More about my engineering approach
I use vibe-coding workflows and AI-agent orchestration to shift development from manual syntax toward high-level architectural intent. The goal is not automation for its own sake: it is a dependable engineering system in which generated changes remain reviewable, testable, source-backed, and ready for real operational constraints.
My core interests include harness engineering, generative AI and big-data convergence, MLOps automation, microservice architecture, Google Cloud and BigQuery, data virtualization, agile development, and human–AI pair programming.
