AI Evaluation Specialist - Remote Quality Assurance

YO AI Labs; Warszawa; Remote; PLN 134,000 - 321,000; Full time

Job summary

YO AI Labs is seeking an AI Evaluation Specialist to assess and improve the quality of AI assistant outputs for an enterprise training project.

You will evaluate responses against rubrics for accuracy and relevance, provide actionable feedback, and help refine evaluation criteria while working remotely as a contractor.

Experience in grading or QA and daily use of AI assistants like ChatGPT or Claude is preferred; no formal AI background required.

Qualifications

• Experience in grading, quality assurance, editorial review, assessment, annotation, or similar analytical work.
• Advanced, daily use of AI assistants such as ChatGPT, Claude, or similar tools.
• Strong ability to analyze complex information and communicate findings clearly in writing.
• Experience with process improvement, rubric development, or quality assessment.

Responsibilities

• Evaluate AI-generated outputs against detailed rubrics for accuracy, relevance, quality, and adherence to guidelines.
• Apply consistent and objective judgment across large volumes of examples.
• Identify reasoning gaps, tool-use issues, logical errors, and inconsistencies.
• Provide concise, actionable feedback highlighting strengths and areas for improvement.
• Participate in discussions around rubric interpretation and evolving quality standards.
• Contribute to process improvements and evaluation best practices.
• Maintain accurate documentation of evaluations and recommendations.

Skills

Quality assurance

Editorial review

Assessment & annotation

AI tools proficiency

Analytical writing

Independent work

Tools

ChatGPT

Claude

Job description

YO AI Labs is seeking an AI Evaluation Specialist to assess and improve the quality of AI assistant outputs for an enterprise training project.

You will evaluate responses against rubrics for accuracy and relevance, provide actionable feedback, and help refine evaluation criteria while working remotely as a contractor.

Experience in grading or QA and daily use of AI assistants like ChatGPT or Claude is preferred; no formal AI background required.