Legal AI Evaluator

Location: Milan, Italy; fully remote with one in-person meeting per month

Compensation: €20/hour, invoiced monthly based on hours worked and reported.

Company

hirify.global is a legal AI product company building a trusted platform for lawyers, law firms, and companies across Europe.

What you will do

• Evaluate AI-generated answers to legal questions.
• Define positive and negative criteria for assessing answer quality.
• Build and review benchmark sets used to measure service quality.
• Compare answers from different AI models and select the stronger response.
• Assess legal accuracy, completeness, source usage, and clarity against predefined criteria.
• Provide evaluations that guide product development and quality improvements.

Requirements

• Qualified lawyer admitted to the Italian Bar (iscrizione all'Albo).
• Active Italian VAT number (Partita IVA) required for invoiced collaboration.
• Solid legal experience in at least one practice area, such as civil, criminal, administrative, banking and insurance, tax, corporate, employment, family, consumer, or insolvency law.
• Excellent command of Italian required.
• Ability to work independently on dedicated platforms and follow evaluation guidelines.

Nice to have

• Familiarity with legal technology or generative AI tools used in legal work.
• Experience evaluating AI systems through benchmarks, A/B tests, or model comparisons.

Culture & Benefits

• Independent remote work with direct contact with the People team.
• One in-person meeting per month for alignment and goal-setting.
• Service agreement as an independent contractor with a VAT number.
• Monthly invoicing based on hours actually worked and reported.

Hiring process

• One 30-minute introductory interview.