Python & AI Engineer

Building Intelligent Systems with Python & LangChain

I architect production-ready AI systems using Python, LangChain, and LLMs — from RAG pipelines and prompt engineering to real-time APIs and voice-enabled agents.

View Featured Project Read My Resume

MHT-ChatRAG — Production AI Assistant with Live2D, RAG & Multi-Provider LLMs

My Capabilities

Going beyond simple integrations to build ecosystems.

🧠

Python & LangChain Development

Build RAG pipelines with LangChain & vector databases
Integrate LLMs (GPT-4, LLaMA, Gemini) into production apps
Design adaptive prompt engineering strategies

⚙️

AI Agent Architecture

Orchestrate multi-provider LLM fallback chains
Build autonomous agents with state machines & memory
Deploy scalable systems with Docker & cloud infrastructure

🔄

APIs REST & Real-Time Systems

Design and consume RESTful APIs for AI services
Implement WebSocket-based streaming architectures
Bridge backend intelligence with responsive frontends

Tech Stack

The tools and frameworks I work with daily.

Python LangChain RAG Prompt Engineering OpenAI GPT LLaMA / Ollama Gemini Node.js APIs REST WebSockets LanceDB Redis PostgreSQL Docker Java ElevenLabs TTS

Vision

I build AI systems that behave less like tools and more like intelligent processes — capable of understanding context, retrieving knowledge, and adapting in real time. With Python and LangChain at the core, I create production-grade RAG pipelines, multi-provider LLM architectures, and voice-enabled agents that deliver measurable business value.

That's exactly the kind of systems I build.