Litigator / Practicing Attorney (US) AI Evaluation Expert

You will help improve AI systems that generate legal content. The work involves reviewing written legal responses, explaining what is right or wrong, and drafting or editing sample language for different litigation situations.

• Evaluate AI-generated legal briefs, arguments, memos, and related responses.
• Find factual errors, legal inaccuracies, weak reasoning, and logical inconsistencies.
• Write clear feedback explaining your corrections and quality judgments.
• Assess complex or ambiguous legal edge cases for model evaluation and calibration.
• Draft or edit legal language and arguments for varied litigation contexts.
• Work asynchronously with a cross-functional team through precise written communication.

This is a remote, flexible, asynchronous contractor role available to candidates in the United States. It is listed as part-time, and no fixed schedule is provided.

• $100 to $160 per hour equivalent, paid per task.
• Professional fluency in English.
• A JD degree from an ABA-accredited U.S. law school.
• An active license in good standing in at least one U.S. jurisdiction.
• Three to 15 years of post-JD legal experience, preferably with litigation as a primary practice area.
• Strong legal writing, analytical reasoning, and ability to explain complex legal concepts clearly.
• Helpful experience includes trial, appellate, or federal court work; a federal or state judicial clerkship; law journal editing; published legal authorship; substantial legal writing; or teaching law.