AI Model Evaluation & Prompting Scientist

Curriculo, Inc.; United States; Remote; USD 85,000 - 125,000; Full time

Job summary

Curriculo, Inc. is seeking an expert to evaluate AI model outputs across data science, statistics, ML, and quantitative problems. You will create expert-level prompts, datasets, and reference solutions to guide model development.

Additionally, you will identify flawed methodologies, statistical errors, and weak quantitative reasoning, then provide structured feedback that improves model capability and performance in real-world tasks.

Qualifications

• Experience at a top company (tech, finance, or research) within the past 7 years.
• Undergraduate degree from a top-ranked university.
• Based in an English-speaking country.
• Clear written communication of technical and statistical concepts.

Responsibilities

• Evaluate AI model outputs on data science, statistics, ML, and quantitative problems.
• Create expert-level prompts, datasets, and reference solutions.
• Identify flawed methodology, statistical errors, and weak quantitative reasoning.
• Provide structured feedback that improves model capability.

Skills

Top company experience

English-speaking country

Clear written communication

Statistical concepts

Education

Undergraduate degree from a top-ranked university

Job description

Curriculo, Inc. is seeking an expert to evaluate AI model outputs across data science, statistics, ML, and quantitative problems. You will create expert-level prompts, datasets, and reference solutions to guide model development.

Additionally, you will identify flawed methodologies, statistical errors, and weak quantitative reasoning, then provide structured feedback that improves model capability and performance in real-world tasks.