Auditors check repository-level software engineering benchmark tasks, reference patches and test runners for correctness and answer leakage. It suits maintainers or long-time open-source contributors with several years of engineering who can spot reward hacking.
Sobre la vacante
Evaluate the quality, correctness, and reproducibility of software-engineering benchmark tasks used to train and evaluate a frontier AI lab's models. You'll assess repository-level tasks, reference patches, test harnesses, and grading integrity — and provide clear, rubric-based written feedback.
Basic Qualifications
- 3+ years professional software engineering
- Real open-source contribution or maintainer experience (merged PRs, committer / maintainer roles)
- Strong ability to audit reference patches, test runners, and Docker isolation, and to detect answer leakage / reward hacking
- Fluency across common ecosystems (Python and at least one of Java / Go / TypeScript / C++)
Preferred Qualifications
- Familiarity with SWE-Bench (Verified) or similar repository benchmarks
- Maintainer history on major Python OSS (Django, Flask, scikit-learn, sympy, pytest, etc.)
- Prior code-review or task-grading experience
Fuente oficial: work.mercor.com. Los detalles pueden cambiar; la página de la plataforma tiene la última palabra.¿Hay algún error en esta oferta? Avísanos.
Cómo conseguir trabajo en Mercor Más trabajos de programación Todas las vacantes de Mercor Cuánto ganan los ingenieros de software Trabajos de entrenamiento de IA para ingenieros de software en EE. UU. ¿Cuánto paga Mercor? ¿Es fiable Mercor? Cómo selecciona Mercor a los candidatos Empleos en EE. UU.
