Quantitative AI Model Evaluation Scientist

Use statistical methods and predictive modeling to evaluate AI outputs remotely for DataAnnotation, with flexible scheduling across approved countries. Technical accuracy matters.

DataAnnotation is seeking an experienced quantitative practitioner to support AI model development. The work involves evaluating generated analysis, solving technical problems, and explaining whether outputs hold up in practice. Your expertise may come from data science, economics, statistics, physics, biology, or another quantitative field.

Key Responsibilities:

• Assess statistical analysis and predictive modeling outputs
• Validate scientific reasoning and data-driven insights
• Develop problems covering forecasting and experimental analysis
• Review and write well-documented analytical code
• Shape AI models through direct technical feedback

Requirements:

• Two-plus years of quantitative hands-on experience
• Comfort writing and reviewing analytical code
• Experience with statistical methods and predictive modeling
• Practical experiment design experience, including A/B testing
• Bachelor's degree in a quantitative field preferred

Bring quantitative analysis, experiment design, coding, and scientific reasoning to DataAnnotation's remote AI evaluation work.