About
Hanab delivers infrastructure projects in energy, installation technology, and connectivity. It develops AI applications to support daily work across its six divisions.
Responsibilities
•Configure and develop the central PostgreSQL database and Qdrant vector database
•Build and manage ETL pipelines between source systems and central storage
•Process project files, contracts, RFQ packages, work orders, and maintenance records into usable datasets
•Configure and optimize embedding pipelines, including selecting chunking strategies for each document type
•Implement data classification rules
•Collaborate with colleagues across divisions to improve source data quality and availability
•Track data quality as a key KPI, identify quality risks, and address them
Requirements
•HBO-level working and thinking ability
•Proven production experience with PostgreSQL and vector databases such as Qdrant, Pinecone, Weaviate, or similar
•Production experience with ETL tooling
•Strong Python skills and experience processing complex document formats
•Knowledge of chunking and embedding strategies and their impact on AI application quality
•Able to work calmly and independently with historically accumulated data
•Professional proficiency in Dutch and English
Nice to have
•Knowledge of data structures in construction and service organizations, including project files, contracts, RFQ packages, work orders, SLA reports, and fault reports
Conditions
•Salary of €5,000–€6,500 gross per month, depending on knowledge and experience
•CAO Metaal & Techniek
•Laptop and mobile phone
•25 vacation days and 13 ADV days based on a 40-hour workweek
•Pension plan and supplementary insurance
•Learning and development opportunities through Hanab Hub
•Bicycle scheme
•One work-from-home day per week
•Wellness initiatives, sports challenges, and informal social activities
