I will build your ai full stack mvp with llm features end to end

C
chlee9
C
chlee9
Cheolhee Lee

About this gig

I take your idea from a blank repo to a deployed AI product that real users can log into.


What you get

- Next.js + TypeScript frontend, typed API, Postgres schema and migrations

- Auth, billing, roles, admin panel and transactional email wired up

- The AI part done properly: streaming responses, tool calling, structured output, retries, cost and latency budgets

- Dockerised deploy, CI pipeline, error tracking and a handover document


Why me

I ship LLM products in production, not demos. Recent measured results: 70% lower p95 latency, 38% lower serving cost, 49% fewer output tokens, and a 125x speedup on a core listing path.


Stack

TypeScript, Next.js, React, Tailwind, Node, FastAPI, Python, Postgres, Supabase, Redis, Docker, AWS, OpenAI / Anthropic / vLLM.


Tell me what the product should do on day one and who it is for. I will reply with a scope, a timeline and the exact package that fits before you order.

Get to know Cheolhee Lee

Cheolhee Lee

AI Full Stack Developer specializing in LLM and RAG optimization

  • FromSouth Korea
  • Member sinceApr 2021
  • Languages

    English, Korean
I keep my employer and my clients unnamed here. I ship production AI systems end to end at an undisclosed B2B AI SaaS company - a sales-automation SaaS and a public-sector AI evaluation platform. Measured: LLM p95 latency -70%, serving cost -38%, output tokens -49% via context caching and structured output. 125x list speedup, threads query 411ms to 1.6ms, bundle 21.7MB to 2.3MB. Re-homed three LLM models to an on-prem DGX with zero downtime; passed TTA review for Korea's AI Verification program. TypeScript, Python, Rust, Go, React, PostgreSQL, AWS, RAG, vLLM, MCP.

My Portfolio