Work that turns problems into systems
Selected work goes deep into the problem, decisions, flow, and outcome. The rest stays as a concise project record.
Selected case studies
-
Generative AI (K-Bot) Per-Type Parsing & Chunking Pipeline
A preprocessing system that lifts RAG quality by routing parsing, chunking, and embedding per document type
Designed a RAG document-processing structure that separates preprocessing paths by document type and usage context Backend · AI/RAG · 2025.11 ~ 2026.02 -
Generative AI (K-Bot) Metadata-Based Document Source Tracking
An end-to-end grounding system that traces inline LLM citations back to chunk metadata and the exact source
Linked answer evidence to exact document locations (page/slide/row), making answers verifiable AI/RAG · Backend · 2025.12 ~ 2026.01 -
Generative AI (K-Bot) Vector DB Structure Design & Embedding Migration
A partition-key multi-tenant design and an embedding-model swap that never stops the service
Replaced per-customer/per-file collection growth with model/dimension-based shared collections, capping physical resource growth Backend · Database · 2025.11 ~ 2026.04
More work
- ↗
Azure-Based External Knowledge Ingestion Pipeline
An event-driven backend that turns documents from internal service portals and SharePoint into RAG knowledge with no manual work
- ↗
LLM Agent Workflow MCP Server (Google Workspace · Microsoft 365)
An MCP server that unifies 13 services into ~100 AI tools so an AI agent can run cross-ecosystem work from natural language alone
- ↗
LS Cable SCR Process Crack-Cause Analysis & Prediction Model
A data analysis project that filtered out abnormal casting-speed segments and analyzed process data to find the causes and control conditions behind wire-breakage cracks