Senior Software Engineer, C++ LLM Eval/Repo Validation

You will help evaluate language models on real software engineering tasks. The work uses open-source repositories, GitHub issues, and test suites to assess how well models handle real-world code.

You may also help identify difficult repositories and issues, work with researchers, and support or lead junior engineers on project tasks.

• Analyze and triage GitHub issues across open-source libraries.
• Configure repositories and development environments, including Docker-based setups.
• Run, modify, and test C++ code locally.
• Review unit-test coverage and software quality.
• Assess language-model performance in bug-fixing scenarios.
• Help identify repositories and issues that are challenging for language models.

What it pays and takes

Pay details are not provided in the listing. The assignment is fully remote and structured as a contractor role.

• Location: Open to candidates in India, Pakistan, Nigeria, Kenya, Egypt, Ghana, Bangladesh, Turkey, or Mexico.
• Schedule: At least 20 hours per week, including four hours of overlap with Pacific Time.
• Duration: Three months.
• Language: Fluent in English.
• Experience: At least three years of software engineering experience.
• Strong C++ skills and the ability to navigate complex codebases.
• Proficiency with Git, Docker, and basic software pipeline setup.
• Comfort running, modifying, and testing real-world projects locally.
• Helpful: Experience contributing to or evaluating open-source projects.
• Helpful: Experience with language-model research or evaluation projects.
• Helpful: Experience building or testing developer tools or automation agents.

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 modern artificial intelligence, including reviewing model outputs and testing how models handle code and other tasks. Experienced software engineers are valuable because their technical judgment helps measure and improve model performance on complex real-world problems.