I’m Med Amin Gnichi. I build document intelligence and LLM systems that turn messy information into answers people can trust, with evaluation, access controls, and real workflows behind them.
A few examples of applied AI, data engineering, and measurable operational impact.
A production RAG assistant for legal documents. OCR makes scanned PDFs retrievable; semantic search and caching reduce repeated calls. Multi-user sessions, role-based access, audit visibility, logging, and a labeled evaluation set support reliable use.
Built multi-format ingestion and retrieval for PDFs, images, and Excel files, connecting chunking, embeddings, and semantic search to backend chatbot workflows.
Built forecasting and reporting systems across supply chain and growth operations, from stock-level prediction to customer cohorts and media-efficiency models.
Parse documents, handle scans with OCR, preserve metadata, and make source material usable.
Design chunking, embeddings, access-aware search, and caching around the user’s task.
Connect retrieval to model behavior through APIs, prompts, permissions, and clear failure handling.
Use labeled questions, feedback, logs, and workflow outcomes to guide the next iteration.
Building a RAG platform with OCR, semantic retrieval, caching, access controls, and a 500+ question evaluation framework.
Owned forecasting, analytics, AI knowledge workflows, and reporting that reduced manual work and supported growth decisions.
Built document ingestion and RAG components for an Azure-based enterprise AI platform.
Built inventory forecasting models and monitoring pipelines, helping reduce stockouts by 25%.
Built a quality monitoring platform for production defects, with searchable records, classification logic, and statistical reporting.
Private College of Engineering & Technology · With honors
Higher Institute of Technological Studies · With honors
I’m interested in AI engineering opportunities and teams working on document intelligence, retrieval, and reliable LLM products.