Data Engineer — Production ETL for AI-ready Legal Data

present of AI; Lombardia; Hybrid; EUR 45,000 - 70,000; Full time

Job summary

present of AI is seeking a data engineer to own the data pipelines behind a legal knowledge base and manage the processing of user-uploaded documents. You will read scanned files, tag content, and anonymize sensitive data while ensuring privacy and data quality at scale.

The role requires about four years of data engineering experience, strong Python skills, and hands-on experience running production ETL pipelines with monitoring.

Qualifications

• 4 years of data engineering experience in production environments.
• Strong Python proficiency for data pipelines and scripting.
• Experience running ETL pipelines in production with monitoring and alerting.
• Fluent in Italian and English; willingness to be based in Milan.

Responsibilities

• Own data pipelines behind a legal knowledge base and the processing of users' uploaded documents.
• Read scanned files, extract text, and tag documents accordingly.
• Anonymize sensitive data and ensure privacy compliance in processing.
• Collaborate with AI Engineering and Legal Engineering to improve data reliability and safety.

Skills

Data engineering

Python

ETL pipelines

Monitoring

Tools

Vector databases

SQL

Job description

present of AI is seeking a data engineer to own the data pipelines behind a legal knowledge base and manage the processing of user-uploaded documents. You will read scanned files, tag content, and anonymize sensitive data while ensuring privacy and data quality at scale.

The role requires about four years of data engineering experience, strong Python skills, and hands-on experience running production ETL pipelines with monitoring.