Description:

Own and manage data pipelines for ingesting, normalizing, and enriching legal records.
Transform messy legal source data into structured, queryable insights for AI products.

Requirements:

4-8 years of experience with production data pipelines and large datasets.
Proficient in Python and SQL for data engineering and analysis.
Hands-on experience with legal data (PACER, court dockets, filings).
Familiarity with AI tools for data extraction and analysis (RAG, semantic search, LLM).
Bachelor's degree in Computer Science, Data Science, or related field.
Ability to work autonomously and critically assess AI outputs.
Bonus: Experience with regulatory data and vector databases.

Skills

Benefits