Remote Data Engineer — AI-Powered Legal Tech

Raydar; United States; Remote; USD 180,000 - 220,000; Full time

Benefits offered by this job

Equity opportunity

Job summary

Raydar is hiring a data engineer to own ingest, normalize, and enrich caselaw and docket records. You will transform PDFs, XML, HTML into clean, queryable data and design LLM-assisted extraction workflows. You will partner with engineers to support RAG and semantic search while running production pipelines on AWS.

Qualifications include 4–8 years of pipeline experience, strong Python/SQL, and experience with PACER or court data. Remote US work with NYC travel and visa constraints apply.

Qualifications

• 4-8 years of experience building and operating production data pipelines with large, dirty datasets.
• Strong Python and SQL skills for pipeline engineering and data analysis.
• Hands-on experience with legal data such as PACER records, court dockets, or court filings.
• Experience with AI for data, including RAG, semantic search, and LLM-assisted extraction, plus PDF parsing, OCR, and document extraction tooling.

Responsibilities

• Build and maintain production pipelines for PACER, NYSCEF, state court systems, published opinions, and other legal records.
• Turn PDFs, scanned filings, XML, and HTML into clean, queryable data.
• Create LLM-assisted extraction workflows for legal text and validate results against source documents.
• Run statistical analyses, improve data quality, and optimize SQL queries.
• Support RAG and semantic search workflows in partnership with full-stack engineers.
• Operate and improve AWS S3 and RDS data systems within established security and compliance guardrails.

Skills

Python

SQL

Data pipelines

RAG

Semantic search

LLM extraction

OCR

PDF parsing

Education

Bachelor's degree in Computer Science or Data Science

Tools

PACER data handling

PDF parsing tools

OCR engines

Vector databases

Job description

Raydar is hiring a data engineer to own ingest, normalize, and enrich caselaw and docket records. You will transform PDFs, XML, HTML into clean, queryable data and design LLM-assisted extraction workflows. You will partner with engineers to support RAG and semantic search while running production pipelines on AWS.

Qualifications include 4–8 years of pipeline experience, strong Python/SQL, and experience with PACER or court data. Remote US work with NYC travel and visa constraints apply.