Remote Software Engineer - Benchmark & Audit Specialist

mercor; United States; A distancia; USD 96.000 - 124.000; Jornada completa

Descripción de la vacante

Mercor seeks a SWE-Bench Task Auditor for a remote contract role. You will evaluate benchmark tasks, audit reference patches and test runners, and provide rubric-based feedback to improve AI model training. Experience with Docker isolation and open-source contributions is essential.

Fluency in Python and at least one of Java, Go, TypeScript or C++ is required. You will work independently to meet deadlines and help enhance AI model performance remotely.

Formación

• 3+ years professional software engineering experience.
• Real open-source contribution or maintainer experience.
• Ability to audit reference patches, test runners, and Docker isolation.
• Fluency in Python and at least one of Java, Go, TypeScript or C++.

Responsabilidades

• Evaluate the quality, correctness, and reproducibility of benchmark tasks.
• Assess repository-level tasks, reference patches, test harnesses, and grading integrity.
• Provide rubric-based written feedback to improve AI model training.
• Audit reference patches, test runners, and Docker isolation to detect leakage and hacking.
• Work independently and asynchronously to meet deadlines and enhance AI model performance.

Conocimientos

Software engineering

Open-source contributor

Docker auditing

Python

Java

Go

TypeScript

C++

Code audit

Herramientas

Docker

Descripción del empleo

Mercor seeks a SWE-Bench Task Auditor for a remote contract role. You will evaluate benchmark tasks, audit reference patches and test runners, and provide rubric-based feedback to improve AI model training. Experience with Docker isolation and open-source contributions is essential.

Fluency in Python and at least one of Java, Go, TypeScript or C++ is required. You will work independently to meet deadlines and help enhance AI model performance remotely.