Remote Quantitative Analyst for AI Benchmarking

Mercor; New York (NY); Remote; USD 90,000 - 130,000; Full time

Job summary

Cincinnatus LLC in the United States seeks experienced data scientists and quantitative analysts to design ground-truth evaluation tasks for frontier models. You will create realistic data-analysis challenges, perform cleaning, compute correlations, test hypotheses, and summarize findings for researchers in a notebook.

This full-time, remote W-2 role covers approximately 35 hours per week and involves collaboration with lab researchers, task design, notebook authoring in Jupyter or Colab, and

Qualifications

• MSc or PhD in statistics, data science, or another quantitative STEM field, or equivalent practical experience in a research-heavy analytical domain.
• 1+ years of experience in a research, research-engineering, or heavy data-analysis role.
• Deep hands‑on data-analysis skills: data cleaning, statistical correlation, hypothesis testing, and careful interpretation of results.
• Proficiency with Jupyter Notebooks or Google Colab for analysis and reporting.
• Working proficiency in Python (pandas, NumPy, or similar) and Git.
• Strong ability to communicate analytical findings in writing for decision-makers.
• Past experience in AI training, model evaluation, or benchmark/task authoring is preferred.
• A perfectionist mindset: high attention to detail, creativity in task design, and the ability to work independently through ambiguous, open‑ended problems.
• Ability to engage reliably for approximately 35 hours per week.

Responsibilities

• Design tasks: Create realistic data-analysis challenges — cleaning messy data, comparing methods, interpreting results — based on the kind of analysis you do every day.
• Author notebooks: Work through your own tasks in Jupyter or Colab, producing clear, reproducible reference analyses.
• Compare methods: Build tasks that ask for a fair comparison between analytical approaches, backed by spot checks and a clear recommendation.
• Evaluate models: Review how models handle your tasks, and check whether their statistics and conclusions actually hold up.
• Work as a team: Compare notes with researchers and fellow experts to keep evaluations consistent and accurate.

Skills

Data analysis

Python (pandas)

Jupyter/Colab

Statistics

Communication

Git

Research experience

Independent work

Education

MSc/PhD in statistics or data science

Equivalent practical experience

Tools

Jupyter Notebook

Colab

Job description

Cincinnatus LLC in the United States seeks experienced data scientists and quantitative analysts to design ground-truth evaluation tasks for frontier models. You will create realistic data-analysis challenges, perform cleaning, compute correlations, test hypotheses, and summarize findings for researchers in a notebook.

This full-time, remote W-2 role covers approximately 35 hours per week and involves collaboration with lab researchers, task design, notebook authoring in Jupyter or Colab, and