BEOMSEOK KIM

@bswebdev

Backend Engineer

Folding AI into systems that solve real business problems.

Based in Korea · ~4 yrs backend · open to Japan, remote, and English-speaking teams.

About

I build backend systems that solve real business problems end-to-end — from requirements to design, implementation, and operation. I don't pick technology for its own sake; I ask how to build a mechanism that keeps delivering value.

Focus

  • Backend & infra architecture
  • System design
  • Folding AI into existing systems
  • Large-scale / high-traffic

Also work across

  • API / DB design
  • ERP (SAP) integration
  • Infra & DB migration
  • Caching

Selected Work

Enterprise ESG (LCA) Data Platform

for a large petrochemical manufacturer

European customers' rising demand for LCA data outgrew Excel and manual work. I designed the backend and the ERP (SAP) integration interfaces for a platform to manage and use that data, coordinating data specs and server setup directly with the client's infra team.

  • NestJS
  • GraphQL
  • MSSQL
  • Nginx
  • Windows Server
  • SAP
  • Claude Code
Result
Selected and optimized storage to improve overall system performance, and drove key technical decisions.
Takeaway
In enterprise DX, aligning stakeholders on data definitions is harder than the implementation. Technical correctness alone isn't enough — I documented the Node.js-vs-Java/Spring concern (single-thread) with Worker Threads and I/O-bound workload evidence to reach agreement.

AI-Powered OCR Data Extraction Pipeline

Extracts product-usage data (e.g. cement volume) from factory forms. Irregular layouts and merged cells were beyond rule-based parsing, so I fed the confidence scores and diffs of two OCR APIs into an AI layer for correction and adjudication — making AI a judgment component in the system, not just automation.

  • NestJS
  • GraphQL
  • AWS
  • Redis
  • Supabase
  • OpenAI API
  • Claude Code
Result
Cut OCR processing cost from ~5–6¢ to ~2–3¢ per item (~55%).
Takeaway
I filled what deterministic rules couldn't with AI judgment — kept verifiable by grounding it in the two OCRs' confidence and diffs, not by trusting a single black box.

YourAiWorkforce

prompt is suggestion, graph is law.

A multi-agent planning pipeline that tames a stochastic 8B local model into behaving deterministically enough to trust — turning a founder's rough idea into a PRD and architecture doc, entirely on a 16GB MacBook at zero API cost. Commercial APIs make multi-agent "just work," but that's the model doing the heavy lifting. So instead of trusting the model, I clamp it: a separate critic, a save-validation gate, response post-processing, and state isolation wrap each probabilistic component in a deterministic shell.

  • LangGraph
  • Ollama (qwen3:8b)
  • deepseek-r1:8b
  • FastAPI
  • SqliteSaver
  • LangSmith
Result
Phase 0 (idea → PRD → architecture) runs end-to-end, fully local. Scope is deliberately capped at Phase 0 as a finished product, given an 8B model's code-generation ceiling.
Takeaway
State isolation has two directions: outbound (a subagent's turns polluting the parent thread) is solved via a separate state and a RemoveMessage finalize; inbound (the subagent's LLM still receiving the parent's messages) is a deliberate trade-off, compensated by a structured briefing packet — not hidden. Determinism comes from the graph, not the prompt.

Phase 1–6 (build / QA / deploy) exist as persona designs — roadmap, not yet wired.

CodeBlog seriesUpdated 2026·07

Shipped

Try!Hanzi

A Korean–Japanese–Chinese hanzi comparison platform over a 10,000-character database — compare readings and meanings across three languages, with automatic "false friends" detection for look-alike characters that mean different things.

  • Next.js 16
  • TypeScript
  • Tailwind
  • next-intl
  • PostgreSQL
  • Prisma
  • Redis

Jamming

A mobile-web (PWA) platform matching amateur musicians in Korea for jam sessions — hosts open sessions by region, genre, and skill level; players apply by instrument and get approved. Kakao OAuth, notifications, and song/venue search built in, with a four-layer test suite.

  • Next.js 16
  • TypeScript
  • Supabase
  • Zustand
  • TanStack Query
  • Playwright
  • Vercel
Live ↗Code ↗Updated 2026·07

Writing