Terminal Science Benchmark Engineer (Contractor)

Turing; United States; Remote; USD 67,000 - 134,000; Full time

Job summary

Turing is seeking Physical Sciences experts to design terminal-based tasks for evaluating AI reasoning and reproducibility in scientific workflows. You will translate physics, chemistry, materials science, astronomy, and computation workflows into benchmark environments with pinned dependencies and executable solutions.

Responsibilities include developing inputs, models, tests, and objective grading criteria, ensuring tasks run without runtime downloads, and validating precision, stability, and

Qualifications

• Ph.D., postdoctoral experience, or equivalent advanced technical experience in a relevant physical-science discipline.
• Strong programming skills in Python, C/C++, Julia, Bash, or another scientific programming language.
• Experience working in Linux or terminal-based environments.
• Experience with numerical methods, scientific modeling, simulations, or quantitative data analysis.
• Ability to create and validate computational scientific workflows independently.

Responsibilities

• Design multi-step terminal tasks based on realistic physical-science workflows and build self-contained environments.
• Create input datasets, structures, parameters, and configurations.
• Implement solutions using Python, Bash, C/C++, Julia or domain tools for simulations and modeling.
• Develop automated tests for numerical accuracy, convergence, and data integrity.
• Ensure reproducibility and diagnose issues related to dependencies, precision, and file formats.

Skills

Python

C/C++

Julia

Bash

Linux

Numerical methods

Scientific programming

Education

Ph.D., or equivalent advanced technical experience in a physical-science discipline

Job description

Turing is seeking Physical Sciences experts to design terminal-based tasks for evaluating AI reasoning and reproducibility in scientific workflows. You will translate physics, chemistry, materials science, astronomy, and computation workflows into benchmark environments with pinned dependencies and executable solutions.

Responsibilities include developing inputs, models, tests, and objective grading criteria, ensuring tasks run without runtime downloads, and validating precision, stability, and