or apply directly on Jobgether's site. We never take the application ourselves.
Is this posting real?
- This role has been open
- 9 days Jobgether's roles stay open a median of 12 days
- Reposted
- No
- Salary listed
- No 0% of Jobgether's roles list one
- Ghost-job risk at Jobgether
- low 0 stale, 0 reposted of 4,675 open
- Hiring momentum
- 24620 roles opened in the last 90 days ↑ up vs. the prior 90 days
- Last confirmed on the employer's board
- 2026-09-17
Measured from postings appearing on and disappearing from Jobgether's own lever board since 2026-08-04. Full hiring picture for Jobgether.
About this role
The SWE-Bench AI Task Auditor role is a freelance position focused on auditing software engineering tasks that are used to train and assess AI models. You will evaluate complex codebases, validate task logic, and ensure that tests and evaluation criteria are reliable and reproducible. The position allows for independent work on project-based assignments, contributing your software engineering expertise to improve AI training workflows.
- benefits
- 1/5
- freshness
- 4/5
- career value
- 4/5
- role clarity
- 4/5
- pay transparency
- 0/5
Scored from the posting itself — how clearly the role is described, how much it says about pay and benefits, and how recently it was listed. Not a judgement of Jobgether as an employer.
What you need
- Experience in software engineering
- Ability to evaluate complex codebases
- Skills in validating task logic
- Experience identifying integration problems and test failures
- Ability to provide actionable feedback for task quality improvement
What you get
- Flexible freelance environment
- Opportunity to work independently on project-based assignments
Worth weighing
- Freelance position may lack job security
- Role involves evaluating existing systems rather than developing new features
Summarised from Jobgether's posting. Read the full original.
Listed by Jobgether on their lever job board, last confirmed open on 2026-09-17. PitchMeAI is not the employer.