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 an AI model’s ability to solve complex competitive programming problems. You will be tasked with creating a unique custom problem absent from all existing online judges, creating a reference solution and creating a robust test suite.
Responsibilities
Design and implement checkers for competitive programming problems with multiple valid outputs, ensuring accuracy and robustness.
Evaluate and validate participant submissions against complex problem statements sourced from platforms like Codeforces.
Collaborate with the customer's team to fine-tune problem requirements and clarify ambiguous scenarios.
Develop clear, maintainable code in C++ to assess diverse outputs and edge cases efficiently.
Document checker logic and communicate intricacies or edge cases in both written and verbal form.
Provide feedback to problem setters and reviewers on potential improvements to test cases and checkers.
Stay updated with evolving competitive programming standards and incorporate best practices into checker development.
Required skills
Expertise in competitive programming and coding problem analysis.
Advanced proficiency in C++ for implementing robust checker solutions.
Strong analytical abilities to interpret complex problem constraints and multiple solution paths.
Exceptional written and verbal communication skills; ability to articulate technical details clearly.
Meticulous attention to detail in code validation and output consistency.
Experience working independently in a remote, collaborative environment.
Commitment to producing high-quality, well-documented code under tight deadlines.
Preferred skills
Prior experience as a problem setter, tester, or checker on major competitive programming platforms.
Schedule details
15hrs+ a week.
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.
Eligibility
Work arrangement: Fully remote
Compensation details
$45–$65 per hour.
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.
Thriveth makes AI data-training work easier to find, understand, and navigate. We replace uncertainty with clear opportunities, realistic expectations, and insights from real application journeys.
Hiring companyMicro1
