Remote Data Scientist – GenAI Benchmark & Task Design

Obsidian; New York (NY); On-site; USD 90,000 - 150,000; Full time

Job summary

Cincinnatus LLC is seeking experienced data scientists and quantitative analysts to design ground-truth evaluation tasks for frontier AI models. The role emphasizes data cleaning, statistical analysis, and clear reporting in notebooks.

This is a full-time, fully remote US position with approximately 35 hours per week, collaborating with researchers to ensure rigorous evaluations that guide AI research decisions.

Qualifications

• MSc/PhD in statistics, data science, or quantitative STEM.
• 1+ years of experience in a research, research-engineering, or heavy data-analysis role.
• Proficiency with Jupyter Notebooks or Google Colab for analysis and reporting.
• Working knowledge of Python (pandas, NumPy, or similar) and Git.

Responsibilities

• Design ground-truth evaluation tasks simulating real research work.
• Author notebooks in Jupyter or Colab, producing clear, reproducible reference analyses.
• Compare methods with a focus on fair evaluation and clear recommendations.
• Evaluate how models handle the tasks and verify findings hold up statistically.
• Collaborate with researchers to maintain consistency and accuracy in evaluations.

Skills

Data analysis

Statistical testing

Independent work

Scientific writing

Education

MSc or PhD in statistics/data science or quantitative STEM

Tools

Jupyter/Colab

Python

Git

NumPy

Job description

Cincinnatus LLC is seeking experienced data scientists and quantitative analysts to design ground-truth evaluation tasks for frontier AI models. The role emphasizes data cleaning, statistical analysis, and clear reporting in notebooks.

This is a full-time, fully remote US position with approximately 35 hours per week, collaborating with researchers to ensure rigorous evaluations that guide AI research decisions.