Note: The job is a remote job and is open to candidates in USA. OMW Consulting is hiring a Senior Data Engineer to support a high-performance agentic litigation engine that combines legal data and artificial intelligence. The role owns the caselaw and docket data layer, building production pipelines, converting unstructured legal documents into queryable data, and developing LLM-assisted extraction, RAG, and semantic search capabilities.
Responsibilities
- Build and maintain production data pipelines ingesting millions of court records from PACER, NYSCEF, state court systems, and published opinions
- Take full ownership of the caselaw and docket data layer
- Convert PDFs, scanned filings, XML, HTML, and other semi-structured inputs into clean, queryable data structures
- Design LLM-assisted extraction workflows using Claude, Gemini, or OpenAI
- Turn unstructured legal text into reliable structured data and actionable signal
- Work closely with full-stack engineers to support judicial behavioural intelligence and AI strategy products
- Run statistical analyses and optimise SQL queries to improve data quality and performance
- Build and improve RAG pipelines and semantic search capabilities using tools such as Pinecone and Voyage AI
- Operate and optimise the AWS data stack, including S3 and RDS
- Develop data infrastructure in line with SOC 2 subservice architecture requirements
Skills
- 4+ years of experience
- 4-8 years of experience building and operating production data pipelines
- Strong Python and SQL skills
- Experience working with PostgreSQL, MongoDB, or similar databases
- Experience processing large-scale, messy, or semi-structured datasets
- Familiarity with PDF parsing, XML and HTML scraping, and document extraction workflows
- Experience designing or operating LLM-powered data extraction pipelines
- Understanding of NLP, RAG pipelines, semantic search, and vector databases
- Experience with AWS services, particularly S3 and RDS
- Familiarity with dbt and modern data engineering practices
- Strong analytical and problem-solving skills
- Ability to work closely with software engineers and translate complex data into reliable product infrastructure
- Ability to maintain at least four hours of daily overlap with Eastern Time
- Previous experience working with legal, court, caselaw, docket, or other highly regulated data would be highly valuable
- Experience working directly with PACER, NYSCEF, state court systems, or published legal opinions
- Experience building data products for legal technology, litigation, compliance, or regulated industries
- Experience with Pinecone, Voyage AI, Claude, Gemini, or OpenAI APIs
- Experience operating data systems within SOC 2 environments
Benefits
- 0.15%-0.25% equity.
- Remote US-based working.
- Visa transfers supported, including OPT and H1B transfers.
- Opportunity to own a critical data layer powering an AI litigation platform.
- Direct impact across legal data infrastructure, AI products, and judicial intelligence.
Company Overview