Data Engineer – GenAI & RAG

PKO Finat Sp. z o.o. is developing a platform for processing and sharing unstructured data such as documents, images, and audio recordings for the PKO BP bank.

• Good knowledge of Python and/or Rust
• Experience in building data pipelines and data processing services
• Practical knowledge of vector databases, especially Qdrant
• Understanding of embeddings, semantic search, metadata filtering, and indexing
• Experience with REST API; knowledge of FastAPI is a plus
• Knowledge of event-driven architecture, e.g., Kafka or Pub/Sub
• Good knowledge of Linux
• Familiarity with relational databases, e.g., PostgreSQL

Nice to have:

• Experience with Kubernetes, Docker, and CI/CD
• Knowledge of GCP, BigQuery, Dataflow, Dataproc, or Pub/Sub
• Knowledge of Apache Airflow, Spark, or Beam
• Experience with OCR, audio transcription, and document conversion
• Knowledge of graph databases, e.g., Neo4j
• Experience with Knowledge Graphs, GraphRAG, or classical RAG solutions

• Build and develop online and offline data processing pipelines
• Process documents, images, and audio recordings, including text and metadata extraction
• Create services and API integrations in Python and/or Rust
• Index data and develop semantic search using Qdrant
• Integrate with embedding models and GenAI solutions
• Deploy, monitor, and maintain solutions with a DevSecOps approach
• Diagnose incidents and ensure quality, performance, and reliability of processes