GenAI Benchmark Research Scientist (Remote, Part-Time)

Obsidian; San Francisco (CA); Remote; USD 120,000 - 160,000; Full time

Job summary

Cincinnatus LLC is recruiting researchers to design and author multi-step evaluation tasks for frontier AI benchmarks. The role emphasizes translating scientific method into practical tasks, with a focus on Python-based analysis, rigorous evaluation, and clear written conclusions.

You will work remotely in the United States for approximately 35 hours per week as part of a full-time W-2 engagement, integrated with leading AI lab teams through Cincinnatus’ extended workforce model.

Qualifications

• MSc or PhD in a STEM field, or in a computational social-science or humanities discipline, or equivalent practical experience in a research-heavy domain requiring data analysis and coding.
• 1+ years of experience in an active research role (academia, industry, or national labs).
• Your own research involves significant computational work: Python-based analysis, simulation, modeling, or data pipelines.
• Strong grounding in experimental design, hypothesis testing, and rigorous evaluation of results.
• Working familiarity with Git, IDEs, and notebook environments (Jupyter or Colab).
• Past experience in AI training, model evaluation, or benchmark/task authoring is preferred.
• A perfectionist mindset: high attention to detail, creativity in task design, strong written communication, and the ability to work independently through ambiguous, open-ended problems.
• Ability to engage reliably for approximately 35 hours per week.

Responsibilities

• Design tasks: Turn the research skills you use every day — designing studies, testing hypotheses, evaluating results — into engaging, multi-step tasks.

Skills

Python data analysis

Experimental design

Hypothesis testing

Notebook environments

Research experience

Git version control

Academic writing/communication

Independent work

35 hours/week

Education

MSc or PhD in STEM or computational social science/humanities

Tools

Git

Jupyter/Colab

Job description

Cincinnatus LLC is recruiting researchers to design and author multi-step evaluation tasks for frontier AI benchmarks. The role emphasizes translating scientific method into practical tasks, with a focus on Python-based analysis, rigorous evaluation, and clear written conclusions.

You will work remotely in the United States for approximately 35 hours per week as part of a full-time W-2 engagement, integrated with leading AI lab teams through Cincinnatus’ extended workforce model.