Senior JavaScript AI Model Evaluator

Prolific; EUA; Teletrabalho; USD 41 000 - 69 000; Tempo integral

Resumo da oferta

Prolific is seeking a JavaScript Specialist to join our Expert Network for training and evaluating AI models using real engineering expertise. You will complete a short assessment and, if successful, participate as a paid contributor from home.

Responsibilities include reviewing AI-generated JS/TS code for correctness, auditing explanations, executing tests, and providing concrete feedback to improve model quality and reliability.

Qualificações

• BS, MS, or PhD in Computer Science, Software Engineering, or related technical field.
• Professional experience building scalable web apps with JavaScript/TypeScript.
• Ability to solve LeetCode Medium to Hard problems in JavaScript.
• Deep understanding of Event Loop, closures, prototypal inheritance, and async patterns.
• High standard for clean code, modularity, readability, and ES6+ practices.
• Ability to spot memory leaks or security issues (XSS, prototype pollution) in generated code.

Responsabilidades

• Evaluate AI-generated JavaScript/TypeScript code for correctness and best practices.
• Validate logic and reasoning in AI explanations for complex algorithms.
• Conduct execution testing in Node.js or browser consoles.
• Annotate model performance and identify inefficient solutions or deprecated methods.
• Refine technical logic in frontend/backend architecture discussions.

Conhecimentos

JavaScript

TypeScript

Event Loop

Async/Await

Code Quality

Formação académica

BS/MS/PhD in CS or related

Ferramentas

Jest

Cypress

Webpack

Vite

Descrição da oferta de emprego

Prolific is seeking a JavaScript Specialist to join our Expert Network for training and evaluating AI models using real engineering expertise. You will complete a short assessment and, if successful, participate as a paid contributor from home.

Responsibilities include reviewing AI-generated JS/TS code for correctness, auditing explanations, executing tests, and providing concrete feedback to improve model quality and reliability.