Software Engineer - Benchmark Auditor

mercor; United States; Remote; USD 96,000 - 124,000; Full time

Job summary

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.

Qualifications

• 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++.

Responsibilities

• 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.

Skills

Software engineering

Open-source contributor

Docker auditing

Python

Java

Go

TypeScript

C++

Code audit

Tools

Docker

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .

Position: SWE-Bench Task Auditor

Type: Contract

Compensation: $70–$90/hour

Location: Remote

Role Responsibilities

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

Qualifications

Must-Have

• 3+ years professional software engineering experience.
• Real open-source contribution or maintainer experience (merged PRs, committer/maintainer roles).
• Strong ability to audit reference patches, test runners, and Docker isolation.
• Fluency across common ecosystems ( Python and at least one of Java / Go / TypeScript / C++ ).

Preferred

• 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.