JavaScript Code Reviewer for LLM Evaluation

The work

You will review public JavaScript repositories and help evaluate how well large language models solve software bugs. The work includes preparing real codebases, running tests, and judging model performance in structured evaluation tasks.

• Analyze and triage issues in public JavaScript libraries.
• Prepare repositories for local use, including Docker-based development environments.
• Set up basic software pipelines and run code locally.
• Review unit-test coverage and assess overall test quality.
• Modify and test code while evaluating model responses to bug-fixing challenges.
• Help identify repositories and issues that provide useful challenges for language models.

What it pays and takes

This is a remote contractor assignment lasting approximately 2 to 3 weeks. Candidates must be comfortable working with complex codebases and communicating in English.

• Pay: $25 per task.
• Schedule: 20 or more hours per week, including 4 hours of overlap with Pacific Time.
• Location: Open to candidates in India, Pakistan, Nigeria, Egypt, Ghana, Bangladesh, Turkey, or Mexico.
• Experience: At least 2 years of overall software engineering experience.
• Skills: Strong JavaScript development, Git, Docker, and basic software pipeline setup.
• You should be able to run, modify, and test real-world projects locally.
• Experience with open-source projects, LLM research or evaluation, developer tools, or automation agents is useful.

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 examples and reviews prepared by people to help artificial intelligence systems improve. In this role, your software engineering experience helps assess whether models can understand code and solve realistic bugs.