Data Engineer with GenAI/LLM

Summary

The primary goal of this role is to enhance the data engineering lifecycle with AI, specifically through the development and maintenance of the Data Packaging Framework. The role is crucial for transforming source data into standardized formats and ensuring effective delivery of Data Products.

• Industry: Banking
• Contract length: 12 months+ prolongation
• Type of contract: B2B Contract
• Salary: 150–170 zł/h
• Work model: Hybrid from Gdańsk or Warsaw (3 days in the office, 2 days remote)

Main Responsibilities

• Build and evolve workflows using LLM/agent assistance to improve developer productivity in data pipeline delivery.
• Implement AI-driven schema review and governance as part of automation.
• Drive AI-supported test automation, including end-to-end test generation and validation.
• Develop data packaging pipelines converting source data into canonical formats.
• Manage SQL-based transformation logic within data pipelines.
• Support the canonical message schema lifecycle, including validation and compatibility checks.
• Contribute to operational stability, documentation, and Architecture Decision Records (ADRs).

Key Requirements

• Strong AI / GenAI capability.
• Hands-on experience building LLM-powered automation for engineering workflows.
• Experience with AI-assisted review flows integrated into CI/CD pipelines.

Nice to Have

• Familiarity with Data Reference Architecture or data product models.
• Knowledge of Airflow, Snowflake, Iceberg, or similar platforms.
• Experience with Big Data, Spark, and/or Scala.
• Exposure to data governance, metadata, and lineage concepts.
• Experience in banking or regulated environments.