Scientific Computing Expert — Physical Sciences

Turing, a leading company in AGI infrastructure, collaborates with cutting-edge AI labs to accelerate the development of advanced models by providing high-quality training data, evaluations, and engineering expertise. They are currently seeking experts in Physical Sciences to contribute to Terminal Bench Science by designing realistic, terminal-based scientific tasks. This role involves translating authentic workflows from physics, chemistry, materials science, astronomy, and computational science into reproducible benchmark environments. The goal is to help assess AI agents’ ability to reason through scientific problems, operate command-line tools, debug calculations, and generate reliable scientific outputs.

Key Responsibilities:
- Design multi-step terminal tasks that reflect realistic physical science workflows, creating self-contained computational environments with fixed dependencies and scientific software.
- Develop input datasets, molecular structures, simulation parameters, experimental data, or model configurations necessary for the tasks.
- Implement expert-level solutions using programming languages such as Python, Bash, C/C++, Julia, or other domain-specific tools, covering areas like simulations, numerical modeling, data fitting, optimization, spectroscopy, molecular analysis, and scientific visualization.
- Create automated tests to verify numerical accuracy, physical consistency, convergence, and output structure, establishing appropriate numerical tolerances, units, boundary conditions, and expected scientific behaviors.
- Ensure tasks are reproducible and execute successfully without requiring runtime downloads. Troubleshoot and resolve issues related to dependencies, numerical precision, solver stability, performance, and file formats.

Required Qualifications:
- Ph.D., postdoctoral experience, or equivalent advanced technical expertise in a relevant physical science discipline such as physics, chemistry, materials science, astronomy, or computational science.
- Strong programming skills in Python, C/C++, Julia, Bash, or other scientific programming languages.
- Proficiency working in Linux or terminal-based environments.
- Experience with numerical methods, scientific modeling, simulations, or quantitative data analysis.
- Demonstrated ability to independently create and validate computational scientific workflows.

Engagement Details:
This is a contractor role requiring a commitment of at least 6 hours per day and a minimum of 40 hours per week, with a mandatory 4-hour overlap with Pacific Standard Time (PST). The contract duration is five weeks, with an expected start date in the near future. Compensation is task-based, with payment of $300 per approved task. Please note that this is a contractor assignment without medical benefits or paid leave.

This opportunity is ideal for physical science professionals who enjoy applying their expertise to create rigorous, reproducible scientific benchmarks and who are comfortable working in terminal environments to support the evaluation of AI capabilities.