Remote AI Quality Analyst (Chinese): Prompt Evaluation

Crossing Hurdles; Malaysia; On-site; MYR 83,000 - 111,000; Part time

Job summary

Crossing Hurdles is seeking an LLM - AI Quality Analyst (Chinese) for a four-month remote contractor assignment. You will design and evaluate multi-turn prompts, assess personalization, grounding, and usefulness, and provide structured feedback to improve model performance.

The role requires strong Chinese reading and writing skills, experience in AI evaluation or data annotation, sharp analytical thinking, and clear, evidence-based communication.

Qualifications

• Strong Chinese language proficiency, including reading and writing.
• Experience in AI evaluation, data annotation, content moderation, or related analytical roles.
• Strong analytical and critical-thinking skills with the ability to evaluate nuanced AI responses.
• Experience designing multi-turn prompts and assessing personalization quality.
• Excellent written communication and ability to provide clear evaluation rationales.
• Active user of a personal Google account and willing to enable required personal data sources.

Responsibilities

• Design and execute multi-turn prompts using personal context and experiences.
• Evaluate AI responses for personalization, grounding, integration, and helpfulness.
• Compare and rank AI-generated responses side-by-side based on quality and relevance.
• Identify incorrect personalization, unsupported inferences, hallucinations, and unnatural responses.
• Provide clear, structured rationales and detailed feedback on model performance.
• Review data usage and maintain proper evaluation and data hygiene.

Skills

Chinese language proficiency

AI evaluation experience

Data annotation

Analytical thinking

Prompt design

Communication skills

Job description

Crossing Hurdles is seeking an LLM - AI Quality Analyst (Chinese) for a four-month remote contractor assignment. You will design and evaluate multi-turn prompts, assess personalization, grounding, and usefulness, and provide structured feedback to improve model performance.

The role requires strong Chinese reading and writing skills, experience in AI evaluation or data annotation, sharp analytical thinking, and clear, evidence-based communication.