Domain Contributor - Evaluation Specialist (AI)

Location: Remote, US

Company

hirify.global is engaging domain experts through Micro1 to support an internal project evaluating and improving advanced AI models.

What you will do

• Design nuanced, domain-specific tasks that probe AI model limits and expose reasoning flaws.
• Write questions and scenarios requiring deep expertise beyond general knowledge.
• Evaluate AI-generated outputs against authoritative primary sources for accuracy and nuance.
• Document missed reasoning, source errors, and other model shortcomings.
• Apply detailed task guidelines and evaluation rubrics consistently.
• Submit clear written and verbal deliverables independently on a rolling basis.

Requirements

• Deep expertise in at least one core domain: history, archival or library science, law, finance, journalism, or technology/industry history.
• Advanced research skills and experience verifying complex claims against authoritative sources.
• Exceptional written and verbal communication skills.
• Ability to follow detailed instructions and evaluation frameworks precisely.
• Availability for approximately 15 hours per week and ability to submit the required minimum number of tasks weekly.

Nice to have

• Hands-on experience with AI model training, annotation, RLHF, or evaluation.
• Experience designing adversarial or “stomp the model” tasks.
• Graduate-level research experience, experience at a Fortune 100 company, or professional fluency in a non-English language.

Culture & Benefits

• Remote contractor engagement with flexible, pay-per-task work.
• Output-based compensation for tasks meeting project specifications; time required may vary by experience and workflow.
• Experts selected for the project are expected to begin their first tasks within 24–48 hours after onboarding.
• Roles are typically filled within 48 hours.