Summary
Filippo Leonelli is an AI Engineer based in Sorrento with a track record of translating unstructured data into scalable, production-ready ML and LLM systems. Over the past several years he’s delivered end-to-end solutions—MLOps, RAG architectures, vector DBs, agentic LLM reasoning, and multimodal pipelines—deployed via Docker/Kubernetes and AWS for real-world use cases like financial document assistants and customer-service chatbots. His background blends academic robotics research and hands-on product engineering, from automating force-control experiments to building Kafka-powered ETL and FastAPI search stacks. Notably, he couples model-centric work (LLMs, semantic search, FAISS/Chroma/Qdrant) with strong software engineering practices to drive reliable inference and automation at scale. He brings entrepreneurial experience from co-founding an indie game studio and freelance full-stack work, which informs a pragmatic, product-focused approach to AI. Filippo is particularly adept at stitching multimodal extraction (YOLO+CLIP) into vectorized knowledge systems that enable complex, rule-driven classification and tool-invoking agent workflows.
3 years of coding experience
9 years of employment as a software developer
Laurea triennale, Ingegneria dell'automazione, Laurea triennale, Ingegneria dell'automazione at Università degli Studi di Napoli 'Federico II'
Laurea Magistrale - Ingegneria dell'Automazione e Robotica, Laurea Magistrale - Ingegneria dell'Automazione e Robotica at Università degli Studi di Napoli Federico II
Italian, English