SWE Bench Engineer (Rust)

You will support AI coding evaluation by working with public GitHub repositories and real software projects. The work focuses on finding meaningful bug-fixing challenges and assessing how language models handle them.

• Analyze and triage issues across open-source Rust libraries.
• Set up repositories and development environments, including Docker-based configurations.
• Review unit-test coverage and assess whether tests are useful and reliable.
• Modify and run codebases locally to evaluate model performance on bug-fixing tasks.
• Work with researchers to identify repositories and issues that create meaningful coding challenges.

What it pays and takes

This is a fully remote contractor assignment for professionals located in LATAM. The contract is expected to last approximately two to three weeks.

• $25 per approved task.
• At least 20 hours per week.
• Four hours of schedule overlap with PST.
• Open to candidates located in LATAM.
• Fluent in English.
• At least three years of software engineering experience.
• Strong Rust programming skills.
• Practical experience with Git, Docker, and basic software pipeline setup.
• Ability to navigate complex codebases and run, modify, and test real-world projects locally.
• Experience contributing to or evaluating open-source projects is helpful.
• Experience with LLM research or evaluation, developer tools, or automation agents is a plus.

How it works

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

About AI training work

AI training is the human work behind systems that learn from examples, including code evaluation and model feedback. Software engineers help assess real code and tests so these systems can improve at solving practical programming problems.