Data Steward / Data Engineer

The role

We’re looking for a Data Steward / Data Engineer to help us build and maintain high-quality datasets with a focus on geographical data (e.g., energy infrastructure such as power stations in Texas). You’ll play a key role in curating, cleaning, and structuring data, writing small automation scripts, and leveraging LLMs to improve data quality and coverage. This role sits at the intersection of data engineering and data stewardship- ensuring our datasets are accurate, reliable, and ready to power downstream analytics and AI solutions.

What you’ll do

• Collect, clean, and structure datasets with a focus on geographical and infrastructure data

• Use LLMs and prompt engineering techniques to automate data enrichment and validation

• Write lightweight Python scripts to transform, clean, and check data quality

• Collaborate with product and research teams to define data requirements

• Ensure high standards of data governance, documentation, and reproducibility

• Continuously improve data pipelines and workflows for scalability and efficiency

Requirements

• 3+ years of experience in data engineering, data stewardship, or related roles

• Strong skills in Python (for scripting, data cleaning, and automation)

• Familiarity with LLMs and their application to data processing tasks

• Experience with data quality frameworks, validation, or governance practices

• Understanding of APIs, databases, and common data formats (CSV, JSON, GeoJSON, etc.)

• Attention to detail and ability to work independently on complex data tasks

• Comfortable working in a bilingual setting (Polish B2+ and English B2+)

Please note that this is a 1-month contract with the possibility of extension. The role can also be performed on a freelance basis. We are looking for a person who is available to start within 1 week