Legal Data Specialist

Filevine•Salt Lake City, UT

About The Position

Filevine is forging the future of legal work with cloud-based workflow tools. We have a reputation for intuitive, streamlined technology that helps professionals manage their organization and serve their clients better. We’re also known for our team of extraordinary and passionate professionals who love working together to help organizations thrive. Our success has catapulted Filevine to the forefront of our field—we are ranked as one of the most innovative and fastest-growing technology companies in the country by both Deloitte and Inc. Our Mission Filevine is building the seamless intersection between legal and business by creating a world- class platform to help professionals scale. Department: You will be joining a high-impact team tasked with building our next-generation AI-first platform. This is a small, agile core team operating with a startup mentality within the larger engineering organization. We value speed, autonomy, and the intelligent use of AI to solve complex automation problems Job Summary: We are seeking a detail-oriented Legal Data Specialist to ensure the accuracy of our AI-first Platform. Your primary focus will be validating complex case data that powers our system. You will help build the evaluation system itself to allow for the scalable growth of the product. By identifying patterns in errors and creating "Gold Standard" datasets, you will provide the critical feedback loop our engineers need to refine the product. You should be comfortable using AI tools to optimize your workflow and increase velocity.

Requirements

Education: Bachelor’s degree in Legal Studies, Political Science, or related field; a J.D. or Paralegal Certificate is a strong plus.
Legal Experience: 2+ years of experience in legal research, docketing, or paralegal work, with deep expertise in reading and interpreting court opinions and rules.
Attention to Detail: Ability to spot minute discrepancies in citations, party names, and dates across thousands of documents.
Agile Experience: Experience working in a fast-paced environment or with software teams, capable of working in 2-week sprints .
Problem Solving: A proactive approach to troubleshooting and a willingness to leverage AI tools to find solutions quickly.
Communication: Strong ability to collaborate with backend engineers and product managers to ensure seamless integration.

Responsibilities

Data Verification: Perform high-volume review of ingested court data (opinions, rules, dockets), comparing AI outputs against original source documents to correct metadata errors and ensure accuracy.
Evaluation Design: Collaborate with the engineering team to define how we measure success, helping to create the "Gold Standard" test sets and validation criteria used to grade our AI models.
Pattern Recognition: Identify and document systemic errors in the data (e.g., "The system consistently misidentifies Plaintiff names in Texas District Courts") to help the backend team improve their ingestion logic.
Data Structure Refinement: Assist in mapping the relationships between courts and judges, ensuring our digital ontology accurately reflects the hierarchy and structure of the US legal system.
Quality Assurance: Regularly audit the platform to spot "hallucinations" or defects, ensuring defect-free releases and minimizing escape rates.
AI Utilization: Actively use AI-driven tools to generate test cases, automate routine checks, and troubleshoot inconsistencies to maintain high velocity.