c
chlee9

Cheolhee Lee

@chlee9

AI Full Stack Developer specializing in LLM and RAG optimization

Coreia do Sul
Coreano, Inglês
Algumas informações são exibidas no idioma inglês.
Sobre mim
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.... Saiba mais

Habilidades

c
chlee9
Cheolhee Lee
offline • 
Tempo médio de resposta: 1 hora

Conheça meus serviços

Consultoria de Tecnologia de IA
I will optimize your llm app for lower latency and cost
A partir deUS$ 180 /projetoMais detalhes
Software e Sites de IA
I will build a production rag system over your documents
A partir deUS$ 300 /projetoMais detalhes

Portfólio

Experiência profissional

Self-Employed_/ Freelancer

AI Full-Stack Developer

Self-Employed / Freelancer • Autônomo

Dec 2022 - Present • 3 yrs 9 mos

Lead AI and full-stack development across a sales-automation SaaS and a public-sector AI evaluation platform. - Cut LLM p95 latency 70 percent, wall time 31 percent and serving cost 38 percent with context caching and structured output; removing HTML body generation cut output tokens a further 49 percent. - Delivered 26x sidebar and 125x list speedups; threads query 411ms to 1.6ms. Front-end bundle 21.7MB to 2.3MB. - Contained a 7.83 percent email bounce incident and rebuilt multi-domain sending with fail-closed validation. - Re-homed three LLM and embedding models to an on-premise DGX with zero downtime, enabling air-gapped public-sector delivery. - Passed TTA technical review for the Korean AI Verification program (aiverify.kr).