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.

Process

• Apply to the role, filling out the screening questions.
• Complete AI Interview (approx. 30 minutes).
• Technical Assessment (Tentative).
• Hiring Manager review.

Start Timeline & Availability

We typically fill roles within 48 hours and are looking for experts ready to jump in right away. If selected, we expect you to start your first tasks within 24–48 hours of completing onboarding.

As an expert you will be creating Reinforcement Learning Environments which test an AI model’s ability to solve complex software engineering problems using Model Context Protocol (MCP) tools. Tasks may involve fixing bugs, implementing features, refactoring code, or optimizing performance while requiring agents to discover and reason over information from real MCP servers. You will design reproducible environments, deterministic verification, and golden reference solutions that accurately measure both MCP tool use and software engineering ability.

• Proficiency in C++, Python, JAVA, GoLang, Typescript, or Rust.
• Deep understanding of algorithms, data structures, and performance tuning.
• Demonstrated experience in debugging complex software issues and delivering maintainable solutions.
• Strong background in feature development and codebase refactoring.
• Proven ability to optimize software for performance and scalability.
• Exceptional written and verbal communication skills, with a keen attention to detail.
• Track record of success in collaborative, cross-functional teams, ideally in remote settings.
• Familiarity with modern AI or machine learning systems is a plus, though not required.

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.