Data Engineer Boulevard Tech · Helsinki

Boulevard Tech is hiring a Data Engineer to build and operate a large-scale data ecosystem: integrating with hundreds of external data sources (public APIs, paid/provider systems, and web extraction), normalizing and enriching data, and feeding it into an ingestion pipeline that embeds content and stores it in a vector database for semantic retrieval.

What you will work on

• Build and maintain data connectors to diverse sources
• Design, implement and improve our data integration and ingestion pipeline
• Normalize and structure heterogeneous data (and metadata) into consistent formats
• Implement document processing: parsing, cleaning, deduplication, chunking, and quality checks
• Generate and improve embeddings and store vectors + metadata in a large-scale vector database to support RAG / semantic search
• Ensure reliability and observability of the entire data pipeline: monitoring and alerting
• Han...