Benchmark Designer in Computational Statistics & Applied Math

Obsidian; Greater London; On-site; GBP 45,000 - 75,000; Full time

Job summary

Obsidian seeks a Computational Statistics and Applied Mathematics Expert to design graduate-level problems for a large-scale AI benchmark. You will craft tasks requiring real scientific software and multi-step workflows, including simulations and result interpretation.

You will work with statisticians and applied mathematicians to shape problems that test reasoning under research conditions, leveraging R/Python packages and reproducible concepts.

Qualifications

• Graduate-level training in statistics, applied mathematics, or equivalent research experience.
• Proven proficiency with at least one specialized statistical, mathematical, or scientific software package.

Responsibilities

• Create problems requiring skilled use of specialized statistical software.
• Design graduate-level problems based on real workflows and research.
• Test problems against AI models and refine for target difficulty.
• Plan queries or experiments to uncover hidden information and narrow options.
• Refine problems through testing with state-of-the-art models.

Skills

Strong Python skills

Linux/terminal proficiency

Graduate-level statistical know-how

Education

MS in statistics / applied mathematics

PhD preferred

Tools

R

Python

Matlab

Scilab

Job description

Obsidian seeks a Computational Statistics and Applied Mathematics Expert to design graduate-level problems for a large-scale AI benchmark. You will craft tasks requiring real scientific software and multi-step workflows, including simulations and result interpretation.

You will work with statisticians and applied mathematicians to shape problems that test reasoning under research conditions, leveraging R/Python packages and reproducible concepts.