Senior AI Data Engineer
New
B
BillenniumIT Services
Warszawa, Tadeusza Czackiego, Warszawa, Country code: PLFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- PythonData engineeringPostgresNLPLLM
Requirements
- 5+ years of professional experience in Data Engineering, Applied Data Science, or Analytics Engineering.
- Proven experience owning and maintaining production-grade data pipelines.
- Strong Python skills for data processing, parsing, cleaning, and pipeline development.
- Hands-on experience managing unstructured enterprise data like PDFs, Office files, and wikis.
- Experience preparing and managing data for retrieval, NLP, or RAG-based use cases.
- Strong understanding of data quality engineering, lineage, and refresh cycles.
- Understanding of RAG and retrieval concepts such as chunking, embeddings, and metadata.
- Ability to collaborate effectively with AI Engineers, Architects, and business stakeholders.
- Experience with Postgres and pgvector or other vector databases.
- Knowledge of hybrid search, filtered retrieval, and reranking techniques.
- Experience with AI observability tools like Langfuse and evaluation frameworks like RAGAS or DeepEval.
- Experience with PII detection and masking tools such as Microsoft Presidio.
Responsibilities
- Lead data discovery and triage for AI use cases by identifying authoritative and trustworthy data sources.
- Clean, normalize, deduplicate, and standardize large volumes of structured, semi-structured, and unstructured enterprise data.
- Build and maintain ingestion pipelines for SharePoint and other enterprise document repositories.
- Design and optimize chunking strategies, metadata enrichment, and document structures for RAG applications.
- Prepare and maintain AI-ready knowledge sets using tools like Postgres and pgvector.
- Define and implement data quality gates and monitoring processes to ensure freshness and accuracy.
- Collaborate with AI engineers to evaluate retrieval performance using frameworks like RAGAS and DeepEval.
- Apply enterprise data governance, privacy, and PII masking patterns such as Microsoft Presidio.
View Full Description & ApplyYou'll be redirected to the employer's site
