SWE Bench Engineer (Java LLM Code Evaluation)

You will assess Java software projects and help measure how well language models handle real bug-fixing tasks. The work involves running, changing, testing, and reviewing open-source code locally.

• Analyze and triage issues in open-source Java libraries.
• Set up repositories, Docker-based development environments, and basic software pipelines.
• Review unit-test coverage and overall code quality.
• Modify and run projects locally to evaluate LLM performance on bug-fixing tasks.
• Find repositories and issues that create meaningful evaluation challenges for language models.
• Work with researchers and, when needed, guide junior engineers on related projects.

What it pays and takes

This is a remote contractor assignment for freelancers in Latin America. It is a one-month contract, and the structured time commitment is 20 or more hours per week.

• Pay: $25 per approved task.
• Location: Open to candidates in Latin America.
• Schedule: 20 or more hours per week, including four hours of overlap with PST.
• Experience: At least three years of overall software engineering experience.
• Technical skills: Strong hands-on Java experience, plus proficiency with Git, Docker, and basic software pipeline setup.
• You must be comfortable navigating complex codebases and running, modifying, and testing real-world projects locally.
• Helpful experience includes contributing to or evaluating open-source projects, participating in LLM research or evaluation, and building or testing developer tools or automation agents.
• Language: Professional fluency in English.

How it works

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

About AI training work

AI training work uses human review to help improve artificial intelligence systems. In this role, software engineers evaluate model-generated code and realistic bug-fixing attempts, so strong engineering experience helps produce reliable feedback.