AI Engineer: LLMs, RAG & Local Inference

Aieng in Rome is seeking an AI Engineer to develop and implement AI-driven solutions focused on local inference systems and agentic workflows. You will integrate AI features into our .NET backend and participate in cross-functional software development.

The role emphasizes LLMs, NLP, RAG pipelines, and vector databases, with hybrid work participation and collaboration across engineering teams.

AI Deployment & Inference: deploy and run open-weight models in our platform. RAG & Agentic Workflows: develop reasoning agents and retrieval pipelines. Model Fine-Tuning: adapt and fine-tune foundational models for our domains. Cross-Functional Collaboration: build AI services in Python that integrate with C# backend. 2+ years of proven software engineering experience in Applied AI or inference pipelines. Degree in Computer Science, AI, or related field; advanced degrees are a plus. Experience with Python and C#/.NET for cross-ecosystem integration. Familiarity with LLMs, NLP, and AI deployment on local inference systems. Experience with vector databases and RAG pipelines.