Data Engineer - Legal AI

OMW Consulting United State
Remote
Apply
AI Summary

Data Engineer for a fast-growing Legal AI startup building intelligent systems to process millions of court records. Owns the caselaw and docket data layer end-to-end. Requires 4-8 years of experience in building production data pipelines.

Key Highlights
Own production pipelines ingesting from PACER, NYSCEF, and state courts at scale
Design LLM-assisted extraction workflows to turn unstructured legal text into structured signal
Collaborate with full-stack engineers on judicial behavioral intelligence and AI strategy layers
Key Responsibilities
Own production pipelines ingesting from PACER, NYSCEF, and state courts at scale across millions of court records
Wrangle messy semi-structured inputs (PDFs, scanned filings, XML/HTML) into clean, queryable structures
Design LLM-assisted extraction workflows using Claude, Gemini, or OpenAI to turn unstructured legal text into reliable structured signal
Collaborate closely with full-stack engineers feeding judicial behavioral intelligence and AI strategy layers
Run statistical analyses, optimize SQL queries, and leverage RAG and semantic search tooling (Pinecone, Voyage AI)
Operate and optimize the AWS data stack (S3, RDS) within SOC 2 architecture guardrails
Technical Skills Required
Python SQL PostgreSQL MongoDB dbt NLP RAG AWS S3 RDS
Benefits & Perks
$180K–$220K + Equity
Remote work
H1B transfers and TNs only — no new visa sponsorship

Job Description


Role: Data Engineer | Legal AI

Location: Remote (US) - working EST timezone

Compensation: $180K–$220K + Equity


I'm partnering with a fast-growing Legal AI startup on a genuinely exciting hire — they're building intelligent systems that process millions of court records to power AI-driven legal strategy, and they need a talented Data Engineer to own the foundation it all runs on.


The Role


This is a high-ownership, high-impact position. You'll own the caselaw and docket data layer end-to-end — building and maintaining production pipelines that ingest, normalize, and enrich data from PACER, NYSCEF, state court systems, and published opinions. Every downstream product surface depends on what you build.


What You'll Be Doing


  • Own production pipelines ingesting from PACER, NYSCEF, and state courts at scale across millions of court records
  • Wrangle messy semi-structured inputs (PDFs, scanned filings, XML/HTML) into clean, queryable structures
  • Design LLM-assisted extraction workflows using Claude, Gemini, or OpenAI to turn unstructured legal text into reliable structured signal
  • Collaborate closely with full-stack engineers feeding judicial behavioral intelligence and AI strategy layers
  • Run statistical analyses, optimize SQL queries, and leverage RAG and semantic search tooling (Pinecone, Voyage AI)
  • Operate and optimize the AWS data stack (S3, RDS) within SOC 2 architecture guardrails


What They're Looking For


  • 4–8 years of experience building production data pipelines
  • Prior fluency with legal data (PACER, NYSCEF, court records) is a significant advantage — it will save months of ramp
  • Strong command of Python, SQL, PostgreSQL, MongoDB, dbt, and NLP/RAG tooling
  • Comfortable working in an AWS environment (S3, RDS)
  • Remote US-based with strong preference for NYC / Eastern Time (4+ hours daily overlap required)


Compensation


  • $180,000 – $220,000 base salary
  • 0.15% – 0.25% equity
  • Remote (US) — NYC preferred
  • H1B transfers and TNs only — no new visa sponsorship


Similar Jobs

Explore other opportunities that match your interests

Senior Data Scientist

Data Science
8h ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

gardyn

United State

Senior Business Data Analyst

Data Science
9h ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Associate

Jobgether

United State

Data Engineer

Data Science
16h ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

TEKsystems

United State

Subscribe our newsletter

New Things Will Always Update Regularly