Scientific Computing Expert — Physical Sciences

Turing is a leading company specializing in AGI infrastructure, collaborating with cutting-edge AI laboratories to accelerate the development of advanced models. The company focuses on delivering high-quality training data, evaluations, and engineering expertise to push the boundaries of artificial intelligence. This opportunity involves contributing to scientific benchmark development by creating realistic terminal-based tasks that test AI agents' reasoning and problem-solving abilities within physical sciences.

Key Responsibilities:
- Design multi-step terminal tasks that reflect authentic workflows in physics, chemistry, materials science, astronomy, and computational science. Develop self-contained computational environments with fixed dependencies and relevant scientific software.
- Generate 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. These solutions may involve simulations, numerical modeling, data fitting, optimization, spectroscopy, molecular analysis, or scientific visualization.
- Develop automated tests to ensure numerical accuracy, physical consistency, convergence, and proper output structure. Define numerical tolerances, units, boundary conditions, and expected scientific behavior for validation.
- 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.
- Proficiency in programming languages commonly used in scientific computing, including Python, C/C++, Julia, and Bash.
- Experience working in Linux or other terminal-based environments.
- Strong background in numerical methods, scientific modeling, simulations, or quantitative data analysis.
- Demonstrated ability to independently create, validate, and maintain computational scientific workflows.

Engagement Details:
This is a contractor role requiring a minimum commitment of 6 hours per day and at least 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 upcoming week. Compensation is task-based, with a payment of $300 for each approved task. Please note that this is a contractor assignment and does not include medical benefits or paid leave.

This role offers the chance to work at the intersection of advanced physical sciences and artificial intelligence, contributing to the development of benchmarks that assess AI capabilities in scientific reasoning and computational problem-solving. Candidates with strong technical skills and a passion for scientific rigor will find this position both challenging and rewarding.