QA Engineer – AI Evaluation

Job Description

micro1 is hiring 30 QA Engineers for a high-volume project combining professional software quality assurance with AI training and evaluation.

You’ll evaluate AI-generated technical outputs, design and assess test cases, review bug reports, identify defects, and provide detailed feedback to help improve next-generation AI systems.

This opportunity requires both a strong software QA background and previous paid human-data experience supporting AI training.

What You’ll Do

• Evaluate and rate AI-generated technical outputs using defined quality criteria and rubrics.
• Identify outputs that appear correct but contain errors, omissions, or other quality issues.
• Design and assess test cases covering functional, regression, edge, negative, and boundary scenarios.
• Review bug reports and testing documentation for completeness and reproducibility.
• Assess whether reported issue severity is appropriate.
• Identify, isolate, and document software defects with clear reproduction steps.
• Use structured bug-tracking and testing workflows.
• Provide detailed annotations and actionable written feedback.
• Collaborate with project teams to improve evaluation guidelines and testing standards.

Requirements

• Professional experience as a QA Engineer, SDET, Test Engineer, QA Analyst, or similar software quality assurance role.
• Strong understanding of test case design, regression testing, bug tracking, and software testing principles.
• Experience with both manual and automated testing strategies.
• Hands-on experience with automation frameworks and test-management tools.
• Previous paid human-data experience supporting AI training is required, such as annotation, labeling, RLHF, AI response evaluation, model evaluation, or rubric-based grading.
• Excellent analytical and problem-solving skills.
• Strong attention to detail.
• Written English proficiency at B2 level or above.
• Reliable internet connection.
• Availability to begin promptly.

Software QA experience alone does not satisfy the project requirement. Applicants must also have prior paid human-in-the-loop AI evaluation or human-data experience.

Tools & Technologies

Relevant experience may include:

Selenium, Playwright, Cypress, Appium, Postman, Jira, TestRail, Zephyr, BrowserStack, or comparable QA and test-management tools.

Education

No formal degree is required. Practical and demonstrable software testing experience takes precedence.

Contract & Compensation

This is a remote contractor opportunity with 30 openings.

Compensation is advertised at $90–$175 per hour.