Ai Engineer: Rag & Llm Production Systems
in Modena, Italy seeks an AI Engineer with 2–4 years of software experience to ship LLM-powered systems.
Tutti i candidati sono invitati a leggere attentamente la seguente descrizione del lavoro e le relative informazioni prima di candidarsi.
You will design end-to-end RAG pipelines, implement embedding strategies, vector retrieval, and response generation, and work with multi-step reasoning.
You will use LangChain, LangGraph, LlamaIndex or custom orchestration, maintain MCP servers, optimize retrieval quality, and contribute to fine-tuning when needed.
xysqume
Strong Python and production-grade coding sense required.
#J-*****-Ljbffr
Tutti i candidati sono invitati a leggere attentamente la seguente descrizione del lavoro e le relative informazioni prima di candidarsi.
You will design end-to-end RAG pipelines, implement embedding strategies, vector retrieval, and response generation, and work with multi-step reasoning.
You will use LangChain, LangGraph, LlamaIndex or custom orchestration, maintain MCP servers, optimize retrieval quality, and contribute to fine-tuning when needed.
xysqume
Strong Python and production-grade coding sense required.
#J-*****-Ljbffr