Scientific Computing Expert — Mathematics PHD

Turing is a leading company in AGI infrastructure, collaborating with cutting-edge AI labs to accelerate the development of advanced models through high-quality training data, evaluations, and engineering expertise. We are currently seeking Mathematics experts to create realistic, terminal-based scientific tasks for Terminal Bench Science. This role involves designing complex tasks that test AI agents’ ability to formulate mathematical problems, implement algorithms, operate within terminal environments, debug workflows, and produce verifiable computational results.

Key Responsibilities
- Design and develop authentic computational mathematics tasks by translating mathematical and research workflows into multi-step terminal environments. These tasks will include datasets, equations, model definitions, constraints, and expected outputs.
- Implement expert-level solutions using programming languages such as Python, R, Julia, C/C++, Bash, or other relevant tools. Areas of focus include optimization, numerical integration, differential equations, matrix computation, statistical inference, stochastic modeling, and algorithm analysis.
- Define rigorous grading criteria encompassing numerical accuracy, convergence, computational complexity, feasibility, and mathematical correctness. Establish appropriate tolerances, stopping criteria, stability requirements, and reproducibility controls.
- Develop automated testing procedures and debug issues by validating results across edge cases and alternative valid implementations. Troubleshoot challenges related to floating-point precision, solver failures, conditioning, convergence, and performance.
- Document all work thoroughly, detailing assumptions, mathematical formulations, expected outputs, and any known limitations to ensure clarity and reproducibility.

Required Qualifications
- Ph.D., postdoctoral experience, or equivalent advanced technical expertise in mathematics, statistics, or a closely related discipline.
- Strong programming skills in at least one of the following: Python, R, Julia, C/C++, Bash, or a comparable language.
- Proven experience working in Linux or terminal-based environments.
- Solid background in numerical methods, optimization, statistics, mathematical modeling, or scientific computation.
- Demonstrated ability to independently implement, test, and validate computational algorithms with attention to detail and accuracy.

Engagement Details
This is a contractor assignment 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 5 weeks, with an expected start date in the coming week. Compensation is task-based, with payment of $300 per approved task. Please note that this is a contractor role without medical benefits or paid leave.

This opportunity is ideal for candidates who thrive in dynamic, technically challenging environments and are passionate about advancing AI capabilities through rigorous mathematical problem-solving and computational science.