I specialize in deploying and optimizing AI models for real-world use. I help businesses reduce infrastructure costs by quantizing Large Language Models (GGUF/llama.cpp), allowing them to run efficiently on standard hardware without losing performance.
I build robust, production-ready APIs using FastAPI and Docker, ensuring your AI tools are easy to integrate and scale. My work focuses on the technical side of
AI—making models faster, smaller, and easier to deploy.