R Engineer (English) for AI Model Evaluation

You will evaluate AI-generated responses and create expert R examples that help improve model quality. The work combines code review, applied statistics, data analysis, and careful written judgment.

• Review responses for accuracy, clarity, prompt adherence, and step-by-step reasoning.
• Find errors in statistical methods, modeling choices, and data-wrangling workflows.
• Fact-check analytical results and compare multiple responses for correctness.
• Write explanations and model solutions that show correct use of R.
• Create detailed prompts and responses for AI training across varied topics.
• Test outputs for inaccuracies or bias and assess their reliability across use cases.

This is remote, part-time contract work for candidates who can evaluate multiple AI responses and explain their decisions clearly.

• Time: 20+ hours per week.
• Language: Excellent written English.
• Experience: At least two years of hands-on R experience in data analysis, statistics, or data science.
• R skills: Strong data wrangling, functional programming patterns, and reusable functions or packages.
• Statistics: Applied knowledge of regression, inference, and model validation.
• Analysis: Experience completing R projects from data cleaning and exploration through modeling and visualization.
• Tools: Familiarity with tidyverse, data.table, ggplot2, and large language models used for coding or code review.
• Education: A bachelor's degree in Statistics, Mathematics, Computer Science, or a closely related quantitative field.