Remote Quantitative Analyst for GenAI Benchmarking

Mercor; New York (NY); Remote; USD 100,000 - 180,000; Full time

Job summary

Mercor platform through Cincinnatus LLC seeks experienced data scientists and quantitative analysts for ground-truth tasks. You will design analytical challenges, author notebooks, and compare methods while evaluating model performance.

This is a full-time W-2 role, remote across the United States, ~35 hours weekly, placed within a leading AI lab. You will work with researchers to ensure rigorous analysis, clear reporting, and practical recommendations for frontier-model evaluations.

Qualifications

• MSc/PhD in statistics, data science, or quantitative STEM, or equivalent experience.
• 1+ years in a research, research-engineering, or heavy data-analysis role.
• Hands-on data-analysis skills: data cleaning, correlation, hypothesis testing, interpretation.
• Proficiency with notebooks for analysis and reporting; Python and Git.

Responsibilities

• Design tasks: create realistic data-analysis challenges and cleaning workflows.
• Author notebooks: produce reproducible reference analyses in notebooks.
• Compare methods: build tasks with fair comparisons and clear recommendations.
• Evaluate models: assess how models handle tasks and whether conclusions hold.
• Work as a team: align with researchers to ensure consistent, accurate evaluations.

Skills

Data analysis

Statistical testing

Python programming

Data cleaning

Communication writing

Independent work

Ambiguity tolerance

Availability 35h/week

Education

MSc or PhD in statistics, data science, or quantitative STEM field

Equivalent practical experience in a research-heavy analytical domain

Tools

Jupyter Notebooks

Google Colab

Git

Job description

Mercor platform through Cincinnatus LLC seeks experienced data scientists and quantitative analysts for ground-truth tasks. You will design analytical challenges, author notebooks, and compare methods while evaluating model performance.

This is a full-time W-2 role, remote across the United States, ~35 hours weekly, placed within a leading AI lab. You will work with researchers to ensure rigorous analysis, clear reporting, and practical recommendations for frontier-model evaluations.