Hamna Mohsin

I’m an AI Engineer with hands-on experience building production-grade AI systems—RAG pipelines, LLM-powered applications, and intelligent data extraction infrastructure deployed to cloud environments. I implement end-to-end Retrieval-Augmented Generation (RAG) pipelines across projects, covering chunking strategies, vector indexing, semantic retrieval, and LLM-augmented response synthesis.

I combine strong AI architecture with practical engineering: RESTful API design, database management, containerization, and automated CI/CD deployment. In an AI Intern role, I built a concurrent e-commerce scraping and AI categorization system, including a 3-layer relational database, LLM API-based data refinement, semantic embeddings, and repeatable cloud releases via GitHub Actions.