Remote AI QA Engineer — Contract Backed by Human-in-the-Loop Testing

SaidGig; New York (NY); Remote; USD 124,000 - 241,000; Full time

Job summary

SaidGig is seeking a QA-focused professional to evaluate AI outputs and help improve how AI systems learn, reason, and perform on a remote contract basis. The role emphasizes high-volume, rigorous testing and requires prior paid human-in-the-loop evaluation experience.

You will design tests, score outputs against criteria, and provide precise, actionable feedback to developers. Strong English communication and reliable internet access are essential to begin promptly.

Qualifications

• Professional QA Engineer, SDET, Test Engineer, or QA Analyst experience.
• Strong QA, testing, test case design, bug tracking, regression testing, and manual/automated testing strategies.
• Hands-on automation framework experience with Selenium, Playwright, Cypress, Appium, Postman, Jira, TestRail, Zephyr, BrowserStack.
• Prior paid experience supporting AI training through human data annotation, labeling, RLHF, AI response or model evaluation, or rubric-based grading.
• Excellent written English communication at B2 level or above.
• No formal degree required.
• Demonstrable practical testing experience is prioritized.
• Reliable internet access and readiness to begin promptly.

Responsibilities

• Evaluate and score AI outputs against quality rubrics.
• Design functional, regression, edge-case, negative, and boundary test cases.
• Review bug reports for reproducibility and severity.
• Document defects with precise reproduction steps.
• Provide actionable feedback to developers.
• Collaborate with project teams to refine evaluation guidelines and testing methods.

Skills

QA Engineer

SDET

Test Engineer

QA Analyst

Education

No formal degree required

Tools

Selenium

Playwright

Cypress

Appium

Postman

Jira

TestRail

Zephyr

BrowserStack

Job description

SaidGig is seeking a QA-focused professional to evaluate AI outputs and help improve how AI systems learn, reason, and perform on a remote contract basis. The role emphasizes high-volume, rigorous testing and requires prior paid human-in-the-loop evaluation experience.

You will design tests, score outputs against criteria, and provide precise, actionable feedback to developers. Strong English communication and reliable internet access are essential to begin promptly.