AI Benchmarking Problem Designer (Remote, Part-time)

mercor; United States; Remote; USD 96,000 - 138,000; Part time

Job summary

Mercor connects elite creative and technical talent with leading AI research labs. This remote contract role asks for graduate-level STEM training and strong Python skills to design and calibrate complex scientific problems.

Work 15-20 hours per week, collaborating asynchronously with AI researchers to improve model performance and data quality. Prior experience with scientific software is valued and Linux familiarity is required.

Qualifications

• Graduate-level training in a STEM field (MS/PhD) or equivalent research experience.
• Proficiency with at least one listed scientific software library, evidenced by publications or open-source work.
• Strong Python skills for problem setups and validators.
• Linux/terminal experience and ability to work remotely.

Responsibilities

• Design computational problems using scientific libraries like libRoadRunner or Tellurium.
• Develop problems to test AI systems' ability to perform complex scientific workflows.
• Calibrate tasks against AI models to hit target difficulty.
• Collaborate with AI research teams to improve outputs and data quality.
• Work independently and asynchronously to meet deadlines.

Skills

Python programming

Independent work

Linux/Unix

Research publications

Education

MS or PhD in STEM

Tools

libRoadRunner

Tellurium

SBML-based tools

Job description

Mercor connects elite creative and technical talent with leading AI research labs. This remote contract role asks for graduate-level STEM training and strong Python skills to design and calibrate complex scientific problems.

Work 15-20 hours per week, collaborating asynchronously with AI researchers to improve model performance and data quality. Prior experience with scientific software is valued and Linux familiarity is required.