About this opportunity
Job Description
Terac is hiring AI Evaluators to assess the accuracy, reasoning, and helpfulness of a digital shopping assistant.
You’ll review real interactions between users and the AI, identify where its responses or product recommendations go wrong, and develop structured evaluation criteria to help improve future model performance.
This is an ongoing remote opportunity requiring a commitment of at least 20 hours per week.
What You’ll Do
- Review real user interactions with an AI-powered shopping assistant.
- Identify logical errors, inaccuracies, and unhelpful product recommendations.
- Analyze where the assistant's reasoning or response quality falls short.
- Create structured rubrics and verifiers for evaluating AI responses.
- Apply consistent quality standards across shopping-related interactions.
- Help identify patterns that can be used to improve the underlying AI model.
Requirements
- Experience in AI evaluation, quality assurance, AI training, or related work.
- Strong analytical skills and attention to detail.
- Ability to identify subtle logical and factual errors in text.
- Familiarity with e-commerce search and online shopping experiences.
- Comfortable developing structured evaluation frameworks and rubrics.
- Prior experience with prompt engineering, complex data annotation, or software testing is beneficial.
- Ability to commit 20+ hours per week.
Application Process
Applicants will need to complete Terac's application requirements, including ID verification and a short screening interview for the AI Evaluator role.
Contract & Payment
This is a fully remote independent contractor opportunity paying $50 per hour. Work can be completed on a flexible schedule, subject to the project's 20+ hour weekly commitment.
Payments are processed weekly, and the engagement may be extended, shortened, or concluded depending on project requirements and performance.
