In this role, you'll apply your expertise to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required — your domain knowledge is what matters.

As an expert you will be creating Reinforcement Learning Environments which test and AI model's ability to solve complex software engineering problems related to fixing code, creating features, refactoring code and optimizing performance. You will be tasked with creating a reproducible environment and golden reference solution for the problem.

• On this project, you will create realistic, interesting, and extremely challenging coding tasks for frontier AI models using your favourite repositories!
• You will design problems that require strong software engineering skills, such as tracking down subtle bugs, building non-trivial features, or improving performance.
• For each task, you will define the problem, build a reproducible environment, and write deterministic verifiers that accept correct solutions across different valid implementations while rejecting incorrect, incomplete, or hard-coded approaches. You will also provide a reference solution showing how the task can be solved.

Work arrangement: Fully remote

• Compensation is output-based; experts are paid per task that meets the project specifications. The time required to complete work may vary depending on the expert’s experience and workflow. Minimum submission requirements apply. Experts must submit a minimum of tasks per week.