Senior AI Data Engineer - RAG-Ready Data Pipelines

Billennium; Kraków; Hybrid; PLN 220,000 - 300,000; Full time

Benefits offered by this job

Udemy for Business

Private medical care

Multisport card

Veterinary package

Language lessons

Shopping vouchers

Job summary

Billennium is seeking a Senior AI Data Engineer / Data Scientist to transform complex, unstructured enterprise data into AI‑ready assets. You will own the data lifecycle for AI use cases—from discovery and cleaning to enrichment, ingestion and retrieval optimization.

You will work with SharePoint repositories, documents, PDFs, Office files and more, preparing data for RAG systems, AI agents and copilots. Collaborate with AI engineers and stakeholders to ensure accuracy, scalability and

Qualifications

• 5+ years of professional experience in Data Engineering, Applied Data Science, Analytics Engineering or related field.
• Proven experience owning and maintaining production‑grade data pipelines.
• Strong Python skills for data processing, parsing, cleaning, normalization and pipeline development.
• Hands‑on experience with unstructured enterprise data (documents, PDFs, Office files, wikis, knowledge bases).
• Experience preparing data for retrieval, NLP or RAG use cases, including embeddings and metadata enrichment.
• Understanding of data quality engineering, validation, monitoring, lineage and freshness.

Responsibilities

• Lead data discovery and triage for AI use cases, identifying authoritative, relevant sources.
• Analyze repositories to identify duplicates, outdated or low‑quality content.
• Clean, normalize, deduplicate and standardize large data volumes.
• Define data inclusion/exclusion criteria for AI systems considering relevance and sensitivity.
• Build and maintain ingestion pipelines for SharePoint and enterprise repositories.
• Process documents, PDFs, Word/Excel files, wiki pages and other content.
• Define and maintain document normalization standards and taxonomy.
• Prepare data for retrieval and RAG applications, including chunking and metadata enrichment.
• Support retrieval optimization and post‑retrieval techniques such as reranking.
• Collaborate with AI Engineers on retrieval interfaces and knowledge integration.
• Establish data quality gates and refresh processes; use frameworks like RAGAS/DeepEval.
• Ensure traceability, privacy and auditability across data pipelines.
• Create reusable data cleanup approaches and metadata schemas.

Skills

5+ years experience

Python

production pipelines

unstructured data

retrieval / RAG

data quality

stakeholder collaboration

Tools

Postgres + pgvector

Langfuse

Microsoft Presidio

Job description

Billennium is seeking a Senior AI Data Engineer / Data Scientist to transform complex, unstructured enterprise data into AI‑ready assets. You will own the data lifecycle for AI use cases—from discovery and cleaning to enrichment, ingestion and retrieval optimization.

You will work with SharePoint repositories, documents, PDFs, Office files and more, preparing data for RAG systems, AI agents and copilots. Collaborate with AI engineers and stakeholders to ensure accuracy, scalability and