ph3About expert.ai /h3 /brpWe build production-grade AI systems for enterprise clients. Our work focuses on Large Language Models, Retrieval-Augmented Generation, agentic architectures, and knowledge-driven AI. We are a lean team of engineers and researchers who move fast and care about the quality of what we ship. /p /br /brh3The Role /h3 /brpWe are looking for an AI Engineer with around 2 to 4 years of experience — someone past the learning phase, who has shipped at least one LLM-powered system to production and knows what breaks, what scales, and what was a bad idea in hindsight. /p /brpYou do not need to have done everything. You need to have done some things well, understand why they worked, and be ready to go deeper. /p /br /brh3What You Will Do /h3 /brul /brliDesign and implement RAG pipelines end-to-end: ingestion, chunking strategies, embedding models, vector retrieval, reranking, and response generation /li /brliBuild agentic workflows using LangChain, LangGraph, LlamaIndex, or custom orchestration — including tool use, memory management, and multi-step reasoning /li /brliIntegrate and prompt-engineer LLMs (GP Claude Sonnet/Opus, Qwen) for domain-specific tasks; contribute to fine-tuning efforts when needed /li /brliDevelop MCP servers and clients to standardize tool and context exposure across AI systems /li /brliMaintain vector databases (FAISS, Pinecone, Weaviate, Qdrant, pgvector)



and optimize retrieval quality /li /brliBuild evaluation pipelines to track hallucination rate, retrieval precision, latency, and output consistency over time /li /brliWrite clean, tested, production-ready Python and contribute to code reviews /li /brliCollaborate with senior engineers and clients to translate requirements into solid technical decisions /li /br /ul /br /brh3What We Expect /h3 /brul /brli2 to 4 years of software engineering experience, with at least 1 to 2 years focused on LLM or applied AI systems /li /brliAt least one production RAG or agentic application under your belt — you know what it took to get it there /li /brliSolid understanding of embeddings, transformer fundamentals, context management, and prompt design patterns /li /brliFamiliarity with Docker /li /brliAble to work with autonomy — you ask good questions, but you do not wait to be told what to do next /li /br /ul /br /brpFormal degrees are welcome but not required. What matters is what you have shipped. /p /br /brh3Nice to Have /h3 /brul /brliExperience with MCP protocols in real projects /li /brliKnowledge graphs or GraphRAG pipelines (Neo4j, Neptune, or similar) /li /brliInference optimization: quantization (GGUF, AWQ, GPTQ), vLLM /li /brliEvaluation tooling: RAGAS, TruLens, or custom eval design /li /brliDomain NLP experience in legal, manifacturing, or healthcare /li /br /ul /p #J-18808-Ljbffr

📌 AI Engineer (Modena)
🏢 Expert System
📍 Modena