Responsibilities
- Assess the functional correctness and code quality of AI-produced JavaScript and TypeScript outputs
- Review AI-provided algorithmic explanations to confirm logical consistency and accuracy
- Run generated scripts in Node.js or browser environments to validate behavior and performance
- Highlight instances of suboptimal code, outdated syntax, or non-existent library references in model responses
- Deliver structured input on how AI models interpret and solve frontend and backend architectural problems
Work Arrangement
On-site — Leeds, UK
Other
- Must be willing to complete paid one-hour tasks requiring focused, uninterrupted effort, though many tasks are shorter
- Flexible scheduling available
- Option to work remotely
- Eligibility to join the platform within 15 minutes after passing assessment
- Invitation to participate in training and evaluating advanced AI models for compensation
- Initial 10- to 15-minute skills assessment to determine suitability for AI evaluation tasks
.png?1769074621){kind=icon}