QA Engineer (Contractor, Remote)
We are seeking experienced QA Engineers to contribute their expertise in software quality evaluation for a high-volume project focused on training next-generation AI systems. In this role, you will help shape how AI models learn, reason, and perform by providing high-quality, real-world input and evaluation.
Required experience: This role requires prior paid experience with human data annotation, Reinforcement Learning from Human Feedback (RLHF), model output evaluation, or rubric-based grading for AI training. General software QA experience alone, without a human-in-the-loop AI evaluation component, does not meet the requirements for this project. Prior AI development experience is not required; domain knowledge and evaluation skills are key.
Scope of Work
- Evaluate and rate AI-generated technical outputs against defined quality criteria and rubrics, identifying answers that may appear correct but are inaccurate or incomplete.
- Design and assess comprehensive test cases for functional, regression, and edge-case scenarios, including negative and boundary tests.
- Review bug reports and test documentation to ensure issues are reproducible, documentation is complete, and severity is properly assessed.
- Identify, isolate, and document defects with precise reproduction steps using structured tracking mechanisms.
- Provide detailed, actionable written feedback and annotations to support efficient resolution by developers without the need for clarification.
- Collaborate with project teams to refine evaluation guidelines and continuously improve testing standards and methodologies.
Qualifications
- Prior paid human data experience supporting AI training—such as annotation, labeling, RLHF, AI response evaluation, model evaluation, or rubric-based grading—is required.
- Professional experience as a QA Engineer, SDET, Test Engineer, QA Analyst, or in a similar software quality assurance role.
- Strong command of QA fundamentals, including test case design, bug tracking, regression testing, and manual and automated testing strategies.
- Hands-on experience with automation frameworks and test management tools such as Selenium, Playwright, Cypress, Appium, Postman, Jira, TestRail, Zephyr, or BrowserStack, or similar tools.
- Strong analytical and problem-solving skills and meticulous attention to detail.
- Ability to communicate complex findings clearly in written English (B2 level or above), with specific, actionable feedback.
- No formal degree is required; practical, demonstrable testing experience takes precedence.
- Reliable internet connection and readiness to begin promptly.