AI Evaluation Specialist/Recent Grad

Location: Remote

Salary: $20–$70 per hour; output-based compensation is provided for tasks meeting project specifications and quality requirements.

Company

hirify.global is engaging contractors for a project focused on advancing artificial intelligence through research and AI model evaluation.

What you will do

• Develop original, challenging question-and-answer pairs to test advanced AI models across diverse subject areas.
• Conduct in-depth research and cross-verify information across multiple reliable sources.
• Create multi-step questions requiring analytical reasoning, synthesis, and critical thinking.
• Test questions against AI models, analyze responses, and refine question difficulty.
• Document research processes with clear citations, evidence, and logical explanations.
• Revise content based on reviewer feedback while maintaining accuracy, clarity, consistency, and compliance with project quality standards.

Requirements

• Strong ability to conduct independent research and critically evaluate information from multiple sources.
• Excellent English writing skills with a high level of precision and clarity; English fluency is required but does not need to be the first language.
• Ability to create nuanced, well-structured questions that assess deep understanding and complex reasoning.
• Strong analytical thinking, problem-solving, and information-synthesis skills.
• Self-motivation, reliability, and accountability when working independently in a remote environment.
• Interest in emerging AI technologies and in evaluating the capabilities and limitations of advanced AI models.
• Recent graduates, advanced-degree holders, and candidates from diverse academic or professional backgrounds may apply if they demonstrate strong research and writing abilities.
• Contributors must complete the specified minimum number of tasks each week and meet submission requirements.

Nice to have

• Previous experience in AI training, model evaluation, research, or content creation.

Culture & Benefits

• Remote, independent working environment.
• Output-based compensation for tasks that meet project specifications and quality requirements.
• Task completion time may vary based on experience and workflow.
• Selected contributors are expected to begin their first tasks within 24–48 hours after onboarding.

Hiring process

• Positions are typically filled within 48 hours.
• Candidates should be ready to begin promptly.
• Selected candidates complete onboarding before starting their first tasks within 24–48 hours.