Lawyers (T14) - AI Content Benchmarking

Legal • Hourly contract • Remote (US) • -/hr

Mercor is partnering with a frontier AI research organization to recruit legal experts who can vet and improve AI-generated legal analysis.

You will combine elite legal reasoning with structured benchmarking tasks that sharpen how AI systems interpret case law, regulatory language, and courtroom narratives.

Key Responsibilities

• Review AI-generated memoranda, briefs, and filings for accuracy, coherence, and legal validity.
• Draft and score legal reasoning questions that benchmark model performance across doctrine and procedure.
• Provide expert insight on U.S. legal frameworks, case law, and persuasive argumentation.
• Support test design efforts that simulate real-world legal scenarios and stress-test AI capabilities.

Ideal Qualifications

• J.D. from a top 14 U.S. law school with outstanding academic performance.
• Two or more years at a top-tier firm, clerkship, or in-house legal department.
• Exceptional legal writing, editing, and critical analysis skills.
• Deep familiarity with U.S. litigation, regulatory language, and comparative citation standards.

Engagement Snapshot

• Schedule: Remote and asynchronous with the ability to set your own hours.
• Duration: 6-8 week engagement with potential for extension.
• Compensation: - USD per hour paid weekly via Stripe Connect.
• Application: Submit a resume, complete a short intake, and expect follow-up within 3-5 business days.

Bring your T14 expertise to a Mercor-backed AI initiative and help define the standard for trustworthy legal reasoning models.