Remote Freelance SWE Bench AI Task Auditor

Jobgether; Poland; On-site; PLN 358,000 - 511,000; Part time

Benefits offered by this job

Remote work

Freelance contract

Job summary

Jobgether is seeking a SWE-Bench AI Task Auditor for a freelance AI trainer project based in Poland. The role focuses on auditing software engineering tasks used to train and evaluate AI models, ensuring realism, rigor, and reproducibility.

You will review codebases, identify issues, and provide clear feedback to improve task quality. The freelance opportunity offers remote work, flexible project-based engagement, and compensation based on experience and location.

Qualifications

• Deep professional experience in software engineering with real-world apps.
• Ability to evaluate tasks against SWE-Bench requirements.
• Strong analytical and problem-solving skills.
• Attention to detail for subtle logic and reproducibility issues.
• Excellent written feedback for technical reviews.
• Ability to work independently on freelance projects.

Responsibilities

• Evaluate SWE tasks for technical accuracy, realism, solvability, reproducibility, and alignment with SWE-Bench standards.
• Review complex codebases and real-world scenarios to verify practical alignment.
• Assess reliability and completeness of tests and evaluation criteria.
• Identify integration issues and logic errors that affect task quality.
• Provide actionable feedback to improve task implementation and evaluation workflows.
• Apply SWE knowledge to ensure AI training tasks meet high standards.
• Document findings clearly so issues can be addressed efficiently.

Skills

Software engineering

Codebase navigation

Analytical skills

Problem solving

Technical feedback

Independent work

Tools

Code review tools

Job description

Jobgether is seeking a SWE-Bench AI Task Auditor for a freelance AI trainer project based in Poland. The role focuses on auditing software engineering tasks used to train and evaluate AI models, ensuring realism, rigor, and reproducibility.

You will review codebases, identify issues, and provide clear feedback to improve task quality. The freelance opportunity offers remote work, flexible project-based engagement, and compensation based on experience and location.