JavaScript Code Reviewer for LLM Evaluation

You will help evaluate how well large language models solve software bugs in real JavaScript projects. The work combines code review, local development, testing, and structured evaluation.

You will work with public JavaScript libraries and open-source repositories. You will also collaborate with researchers to find repositories and issues that create useful challenges for AI models.

• Analyze and triage issues in public JavaScript libraries.
• Prepare code repositories for local execution, including Docker-based development environments.
• Set up basic software pipelines and navigate complex codebases.
• Review unit-test coverage and overall test quality.
• Run and modify code locally, then assess model performance on bug-fixing tasks.
• Evaluate open-source repositories and issues for use in LLM research.

What it pays and takes

This is a remote contractor assignment for candidates in the listed countries. The assignment lasts approximately 2 to 3 weeks and includes required overlap with Pacific Time.

• Pay: $20 per approved task.
• Time: 20 or more hours per week.
• Schedule: Approximately 2 to 3 weeks, including 4 hours of overlap with Pacific Time.
• Location: Open to candidates in India, Pakistan, Nigeria, Egypt, Ghana, Bangladesh, Turkey, or Mexico.
• Language: Professional fluency in English.
• Experience: At least two years of overall software engineering experience.
• Skills: Strong JavaScript development skills, plus Git, Docker, and basic software pipeline setup.
• Useful background: Open-source contributions or evaluation, LLM research or evaluation, developer tools, or automation agents.

How it works

Apply on OpenTrain with your resume and then complete the application on the hiring site.

About AI training work

AI training work uses human judgment to help improve artificial intelligence systems. In this role, your software engineering experience helps assess whether models can understand code, fix bugs, and produce reliable changes.