STEM Researcher — Computational Fields

DESCRIPTION

A leading AI lab is building the next generation of agentic evaluation benchmarks for frontier models and is recruiting researchers from computational STEM fields — as well as computationally heavy social sciences and humanities — to bring working-researcher rigor to benchmark design. You will translate the scientific method — experimental design, hypothesis testing, and rigorous evaluation — into complex, multi-step tasks that today's best models cannot yet complete reliably. Each task represents one to two days of continuous, focused effort and spans multiple skills: study design, implementation in code, data analysis, and careful written conclusions. You will work in a tight feedback loop with the lab's researchers, surfacing the kinds of methodological mistakes a working researcher would catch immediately. This is a full-time W-2 employment position with Cincinnatus LLC, with the opportunity to be placed at a leading AI lab as part of their extended workforce. This role is fully remote within the United States, at approximately 35 hours per week. 2. Key Responsibilities Design tasks: Turn the research skills you use every day — designing studies, testing hypotheses, evaluating results — into engaging, multi-step tasks. Author solutions: Work through your own tasks in Python and notebooks, at the level of rigor you'd expect from a careful colleague. Define what good looks like: Help spell out what separates sound scientific reasoning from reasoning that merely sounds right. Evaluate models: Review model attempts at your tasks and flag the mistakes a working researcher would spot right away. Work as a team: Compare notes with researchers and fellow experts to keep evaluations consistent and accurate. 3. Core

REQUIREMENTS

• ▸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.

More Mercor contracts