AI/Data Engineer | RAG & Enterprise Search | Remote / Rome-based | Contract (4 Months)
Dopo aver letto questa descrizione, invii il suo CV e le eventuali informazioni aggiuntive richieste facendo clic sul pulsante di candidatura.
We're hiring an AI/Data Engineer for a 4-month contract with a well-established international organisation. This is a hands-on build role — you'll be designing and shipping the data ingestion, vector indexing, and RAG pipelines that power an enterprise AI search application from the ground up.
What you'll be building:
* Scalable ingestion pipelines pulling from SharePoint, web crawls, and enterprise content sources into Elasticsearch/equivalent
* Semantic chunking strategies, metadata extraction, and document conversion pipelines (PDF, Word, PPT, HTML, scanned docs → structured Markdown)
* Hybrid search: keyword + vector + metadata filtering + re-ranking
* Full RAG pipeline: retrieval, prompt orchestration, LLM grounding, fallback strategies
* Agentic workflows with tool calling, multi-step reasoning, and enterprise API integration
* Secure, scalable FastAPI endpoints exposing ingestion, search, and RAG capabilities
What we need from you:
* Strong Python and data engineering fundamentals
* Hands-on experience with Elasticsearch, OpenSearch, or Azure AI Search
* Real RAG application experience — production-grade, xjrgpwk not proof-of-concept
* Experience with LLM orchestration frameworks (LangChain, LlamaIndex, Haystack, or similar)
* Embedding models, cross-encoders, re-ranking, and retrieval technique experience
* Agentic AI workflow and tool-calling experience
Start: Immediate
Duration: 4 months
Location: Remote / Rome
Interested? Apply here or DM/ email me directly at .