Raydar
Data Engineer
$180K–$220K
United States · Remote · Full-time · Posted Sep 30, 2026
- Experience
- 4-8 years building and operating production data pipelines with large, dirty datasets.
- Education
- Bachelor's degree in Computer Science, Data Science, or a related field.
- Visa sponsorship
- Visa transfers may be considered. New visa sponsorship is not available.
About the job
Build and operate pipelines that transform legal records into reliable data for research and AI products.
What you'll do
- Build pipelines for legal records and convert PDFs, scans, XML, and HTML into queryable data.
- Develop and validate LLM-assisted extraction; analyze data quality and optimize SQL queries.
- Support RAG and semantic search, and operate AWS S3 and RDS systems within security and compliance guardrails.
What they ask for
- Strong Python and SQL skills.
- Hands-on experience with legal data, such as PACER records, court dockets, or court filings.
- Experience with RAG, semantic search, LLM-assisted extraction, and PDF parsing, OCR, or document extraction tooling.
- Bachelor's degree in Computer Science, Data Science, or a related field.
Nice to have
- Experience with regulatory or government data sources.
- Experience with vector databases or semantic-search tooling such as Pinecone or Voyage AI.
Pay
$180,000-$220,000 USD (base salary)
Tools
Python, SQL, PACER, RAG, Pinecone, Voyage AI, AWS S3, RDS
AI focus
Create LLM-assisted legal-text extraction workflows and support RAG and semantic search.
Model-written summary · the original posting is authoritative