QA Tester (Remote)

Joblet-AI; United States; À distance; CAD 28 000 - 55 000; Temps partiel

Résumé du poste

Joblet-AI is seeking methodical evaluators to review AI-generated voice, image and video outputs on a remote, hourly contract basis. You will apply defined checks, compare paired outputs for consistency, and provide written rationales. Strong English, reliable internet, and a quiet workspace are required.

Open to students, grads, and professionals residing in eligible countries. The role offers flexible hours and project-based assignments, with a focus on rigorous quality assessment and clear

Qualifications

• Fluent spoken English and clear written communication are required.
• Ability to find consistent faults while following a rubric.
• Ability to explain how details support quality judgments.

Responsabilités

• Apply defined checks to generated outputs and identify repeatable observable errors.
• Compare paired outputs for errors, missing details, clarity and prompt alignment.
• Explain which observable details support your quality judgment.
• Take part in English conversations with AI models when assigned to voice tasks.
• Record your ratings and written explanations without using AI tools.

Connaissances

English communication

Attention to detail

Consistency in checks

Independent work

Description du poste

• Location: Remote from US, CA, UK, IE, AU, NZ
• Engagement Type: Freelance / Hourly Contract

Applicants must currently reside in Australia, Canada, Ireland, New Zealand, the United Kingdom or the United States.

Overview

We are looking for methodical people who spot observable problems and apply checks consistently. You will apply defined checks to generated outputs and identify repeatable observable errors while evaluating AI-generated voice, image and video content. This opportunity is remote, with flexible hours and assignments based on project availability. Students, recent graduates and working professionals are welcome to apply.

Key Responsibilities

• Apply defined checks to generated outputs and identify repeatable observable errors.
• Compare paired outputs for errors, missing details, clarity and prompt alignment.
• Explain which observable details support your quality judgment.
• Take part in English conversations with AI models when assigned to voice tasks.
• Record your ratings using project guidelines and flag examples that are difficult to judge.

Requirements

• Confident spoken English and clear written communication.
• Ability to find consistent faults while following the supplied rubric.
• Ability to repeat defined checks and flag uncertain cases consistently.
• A computer, reliable internet and headphones, with a quiet space for voice-based tasks.
• Ability to produce your own ratings and written explanations without using AI tools.

We welcome applications from qualified individuals of all backgrounds. Applicants are considered based on relevant skills, qualifications and project eligibility requirements, without discrimination on grounds protected by applicable law.