Based in South Korea · Remote worldwide
I ship LLM features into production, build custom agents and automate the workflows that eat your team's time. No hype, just code that runs.
Five sharp offers, from LLM integration to straight-up full-stack work.
Domain chatbots, internal assistants, specialized agents with RAG. I design, build and ship full AI apps wired into your data and systems. Auth, permissions, observability, cost control. Stack: TypeScript, Next.js or Astro, Postgres, pgvector or Qdrant, Claude and GPT.
Adding AI features to a live SaaS or app: suggestions, generation, classification, extraction, semantic search. Streaming, retries, multi-provider fallback, caching, per-user budgets. I plug in OpenAI, Anthropic, Mistral or self-hosted open-source models depending on constraints.
Multi-step workflows that replace manual work: document parsing and classification, structured scraping, PDF and email extraction, cross-tool sync. Solid orchestration, queues, retries, readable logs. N8n or custom code depending on volume.
When you just need a solid developer. SaaS, dashboards, APIs, client portals, back-offices. Modern stack: TypeScript, Next.js, Astro, Node, Postgres, Cloudflare. Clean deploys, simple CI, monitoring. No over-engineering.
For SMBs that want to start without getting burned by the hype cycle. I review your processes, pick the use cases that actually pay off, and tell you what is worth doing and what is not. Deliverables: summary brief, prioritized roadmap, cost and ROI estimates.
Remote from South Korea. I cover EU, US and APAC business hours.
TypeScript, Next.js, Astro, Node, Python, Postgres with pgvector, Cloudflare Workers, Anthropic Claude and OpenAI. I pick the right tool for the problem, never the other way around.
Fully remote from South Korea. I cover EU mornings and US or APAC evenings. On-site visits are possible occasionally, on request.
Fixed quote after a free 30-minute scoping call. As a ballpark: an LLM integration starts around €5–15k, a full-stack MVP around €15–40k.
An LLM integration or AI feature ships to production in 2 to 6 weeks. A full-stack MVP runs 4 to 10 weeks. I'd rather ship a useful V1 fast than a perfect system that never arrives.
Yes, on request. I offer monthly maintenance contracts: monitoring, fixes, small improvements, LLM model upgrades. No long-term lock-in.
SMBs, scale-ups and product teams. From seed and Series A up to mid-market. I also take short engagements for larger groups through their tech leadership.
30 free minutes to scope your need and figure out whether I am the right fit.