Taym Mehdi

Designed and implemented a production-style Retrieval-Augmented Generation (RAG) system for document-based question answering. • Built a FastAPI backend with clean modular architecture (routers, services, schemas) • Implemented document ingestion pipeline with sentence chunking, embedding, and vector storage • Integrated ChromaDB as a persistent vector database • Developed semantic search using sentence-transformer embeddings • Implemented context construction and grounding for LLM prompts • Integrated Ope

Master’s studies in Computer Science with a focus on Artificial Intelligence and Natural Language Processing. Coursework and research-oriented projects in machine learning, NLP, and modern AI systems.

Bachelor’s degree in Information Technology Engineering with specialization in Artificial Intelligence. Strong foundation in algorithms, data structures, machine learning, and AI fundamentals.