RAG / Retrieval Engineer

Main mission

Builds semantic search systems and vector databases that anchor LLMs.

5 key responsibilities

• Design document ingestion and slicing pipelines.
• Build vector and hybrid indexes (embeddings + keywords).
• Optimize relevance: reranking, filters, retrieval evaluation.
• Anchor LLM responses in sources with reliable citations.
• Maintain knowledge freshness and manage access rights.

Key skills

Embeddings, vector databases, hybrid search, relevance evaluation, LLM.

What's expected

Responses anchored in the right sources: RAG is the building block that makes LLMs reliable in business.

Career paths

AI Agents Architect, Senior Search Engineer, AI Solutions Architect.