RAG Engineer: Azure AI Retrieval & GenAI Pipelines

Nebiru; Brussel Hoofdstad; On-site; EUR 70,000 - 100,000; Full time

Job summary

Nebiru in Brussels, Belgium seeks a skilled data/GenAI engineer to design and implement scalable retrieval-augmented generation pipelines. You will handle ingestion, chunking, embeddings, and model generation while optimizing vector storage and hybrid search strategies.

Proficiency in Python, SQL, Spark and Azure services is essential, as is experience with LLM orchestration frameworks. Strong communication and multilingual capabilities are a plus.

Qualifications

• University degree in computer science or quantitative field required; Master's preferred.
• 3+ years in data, ML or GenAI engineering with hands-on RAG or retrieval experience.
• Strong Python, SQL and Spark experience.

Responsibilities

• Design, build and maintain scalable RAG pipelines covering ingestion, chunking, embeddings, retrieval and generation.
• Build ingestion and refresh flows using Azure Data Lake, Databricks and Azure Data Factory.
• Select and optimise vector stores, embedding models, hybrid search and reranking approaches.
• Work with multilingual documents, scanned PDFs, tables and different document versions.
• Evaluate and improve retrieval and generation quality using metrics and frameworks.
• Collaborate with data engineers, data scientists and business analysts to productionise AI use cases.
• Implement monitoring, feedback loops and cost/latency management.
• Apply GDPR, responsible-AI, access-control and document-level security practices.

Skills

Python

SQL

Spark

RAG retrieval

Communication

Education

Bachelor's or Master’s degree in CS/data science/AI/ML/statistics

Master's degree preferred

Tools

Azure Data Lake

Databricks

Azure Data Factory

Azure Synapse

Azure OpenAI

AI Search

LangChain / LlamaIndex / Semantic Kernel

Job description

Nebiru in Brussels, Belgium seeks a skilled data/GenAI engineer to design and implement scalable retrieval-augmented generation pipelines. You will handle ingestion, chunking, embeddings, and model generation while optimizing vector storage and hybrid search strategies.

Proficiency in Python, SQL, Spark and Azure services is essential, as is experience with LLM orchestration frameworks. Strong communication and multilingual capabilities are a plus.