Legal AI Research Contributor

Overview

This role is for Subject Matter Experts with experience in legal practice, restructuring and insolvency, litigation support, or legal operations. The work involves creating realistic Excel-based tasks that test how well AI can perform tasks typically completed by legal professionals.

You will design and validate Excel tasks drawn from your own experience, especially around claims analysis, damages calculations, and spend trackers. You should be familiar with using AI tools in your own work and be able to translate that experience into tasks that can be graded accurately.

Responsibilities

• Create realistic Excel tasks based on your own work, including:
  • Extending existing models
  • Fixing broken models
  • Building models from a brief
• Work through each task yourself to ensure there is a clear, correct answer
• Write yes-or-no grading criteria precise enough for an automated grader to evaluate any attempt against the expected outcomes

Necessary Qualifications

• 3+ years of experience in legal practice, restructuring/insolvency, litigation support, or legal operations, covering disputes, insolvency, commercial or corporate matters
• Deep hands-on Excel skills, including familiarity with:
  • Claims registers
  • Damages calculations
  • Data cleaning
  • Multi-criteria lookups
  • Error tracing
• Strong written English communication skills
• Attention to detail, plus willingness to learn AI and Evals concepts

Preferred Qualifications

• Experience using AI tools in your own work, including identifying and correcting errors

Compensation & Benefits

• Payment is task-based
• Experts who complete their first task within the required timeline will then be qualified to do multiple tasks for the remainder of the project
• Payments will be weekly following task completion
• Engaged as an independent contractor

Location

• Fully remote role that can be completed on your own schedule

Additional Information

• Start Date: Immediate
• Duration: Approximately 4–6 weeks
• Projects can be extended, shortened, or concluded early depending on needs and performance
• Work will not involve access to confidential or proprietary information from any employer, client, or institution

Getting Started (Onboarding Requirements)

• Submit an application with your details and CV
• Attend a 30-minute group walkthrough call
• During onboarding, create one original task from your own work and submit:
  • The brief
  • The actual input workbook(s) needed to complete the task
• Input-file uploads are compulsory
• The brief must be written by you
• Input workbooks must also be human-built
• Use real data that has been sanitised, or public data with the source named
• No AI usage allowed
• Tasks will be run against current frontier AI models. If models get it wrong, you will write a detailed yes-or-no rubric, and a reviewer will sign off on the task with you
• Completing onboarding does not guarantee a job offer; selection remains subject to written approval of the task proposal