AI Engineer / LLM Engineer focused on building production-ready LLM systems,
especially Retrieval-Augmented Generation (RAG).

I specialize in designing end-to-end AI services — from data ingestion and retrieval pipelines
to API servers and real iOS applications used by users.

• LLM system design (RAG, prompt engineering, evaluation)
• Embedding-based retrieval & vector search
• AI backend architecture with FastAPI
• LLM-powered iOS applications (Swift / SwiftUI)
• Clean, scalable service & repository architectures