Engineer (RAG LLM Azure)

As part of the launch of a strategic large-scale AI platform, an AI Engineer is sought to contribute to the production of an intelligent search engine based on RAG (Retrieval-Augmented Generation) technologies. This service, intended for thousands of internal users, forms the first building block of a rapidly expanding AI ecosystem (future use cases, industrialization, scalability).

What you will do.

• You will be involved in the Build & Early Run phases, with a strong technical impact:
• End-to-end implementation of a RAG pipeline
• Retrieval / reranking / LLM orchestration
• Management of citations and response quality
• Development of the ingestion pipeline
• Connectors (CMS, SharePoint…)
• Chunking / embeddings / indexing
• Implementation of security mechanisms (ACL, filtering)
• Design of prompts & guardrails
• Construction of the evaluation framework (metrics, test sets, automation)
• Industrialization via:
• Terraform (IaC)
• Helm / Kubernetes (AKS)
• Participation in optimization and initial run (monitoring, tuning)

What they ask

• Solid experience in AI Engineering / ML Engineering
• Concrete experience with RAG in production (key criterion)
• Proficiency in Python + Azure ecosystem
• Expertise in:
• Terraform & CI/CD (Azure DevOps)
• Kubernetes / Helm (AKS)
• Good understanding of distributed systems and data pipelines
• Ability to build scalable and industrialized solutions