AI Model QA & Red-Team Analyst (Remote)

DataAnnotation; South Carolina; Remote; USD 55,000 - 207,000; Full time

Benefits offered by this job

Flexible schedule

Remote work

Job summary

DataAnnotation is seeking contributors who can vibe-code with frontier models on real engineering tasks, fix bugs, extend APIs, and ship features while evaluating the model’s outcomes against production standards.

You will document failures, explain reasoning, and help improve next-generation coding agents through rigorous red-teaming and clear written explanations. Flexible, remote, project-available work style is emphasized.

Qualifications

• Relevant experience shipping production code in professional or serious open-source contexts.
• Ability to explain technical concepts clearly in writing.

Responsibilities

• Vibe-code with frontier models on real tasks: fix a bug, extend an API, ship a feature, and see how far the model gets on its own.
• Analyze the AI's work against production standards: find the bugs, explain the failure, and rate the model's reasoning.
• Red-team the models to expose unsafe code, faked test passes, and confidently wrong solutions before real users hit them.

Skills

Production coding

Open-source contributions

Clear written English

Bug fixing

Job description

DataAnnotation is seeking contributors who can vibe-code with frontier models on real engineering tasks, fix bugs, extend APIs, and ship features while evaluating the model’s outcomes against production standards.

You will document failures, explain reasoning, and help improve next-generation coding agents through rigorous red-teaming and clear written explanations. Flexible, remote, project-available work style is emphasized.