Data Engineer - Unstructured Data / LLMs

• Design and maintain scalable production data pipelines
• Ingest, clean, and structure large unstructured datasets
• Build OCR, PDF parsing, and document extraction workflows
• Develop semantic search and LLM-assisted retrieval systems
• Improve pipeline reliability, performance, and scalability
• Collaborate closely with engineering and product teams

• 4+ years of experience building production data pipelines
• Experience with law firm data
• Strong Python and SQL skills
• Experience with ETL/ELT, OCR, and document extraction tooling
• Familiarity with RAG, semantic search, vector databases, and AI-assisted extraction workflows
• Experience handling large, messy, or external/regulatory datasets
• Comfortable working autonomously in fast-paced environments
• Bachelor’s degree in CS, Data Science, or related field preferred

Preferred:

• Startup experience
• Experience with AI-enabled products or retrieval systems

Keywords: Python, data pipelines, dbt, (Airflow or Dagster), startup or reputable company: Meta/Palantir