History Expert AI Evaluation

Create and assess historical evaluation material for AI models. Your work will test whether responses use evidence responsibly and recognize the limits of historical interpretation.

• Write scenarios that test source criticism, historical methods, and competing explanations for events.
• Prepare reference answers showing how evidence supports or limits an interpretation.
• Rate AI responses for factual accuracy, historical context, and awareness of different historical interpretations.
• Flag responses that distort evidence, invent causes, or project present-day assumptions onto the past.

What you need and what it pays

• Pay: $50 to $100 per hour, paid weekly through Stripe.
• Schedule: Part-time contractor work with a commitment of 20 or more hours per week. There is no stated maximum, and workload can vary from week to week.
• Location: Remote, open to candidates in eligible countries.
• Language: Clear written English is required.
• Education and experience: An advanced degree in history or a closely related field, plus at least two years of teaching, research, archival, or published historical work.
• Skills: Deep knowledge of a historical period or region, experience with primary sources, and the ability to weigh conflicting sources and explain what the evidence supports.
• Helpful experience: A PhD with peer-reviewed publications, archival research, public history work, or reading knowledge of relevant research languages.

How to apply

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training work uses human examples and judgments to help AI systems learn, including writing scenarios and evaluating model responses. Historical expertise helps ensure that evaluations distinguish evidence-based reasoning from confident but unsupported claims.