Looking for a job

zhiran peng

@zhiranpeng

AI Product Evaluator for Simplified Chinese who tested DeepSeek V4 Flash with a 15-prompt study and six-dimension rubric.

China

Message

What I'm looking for

Remote part-time or contract roles in AI product evaluation, Chinese language quality review, and model output evaluation. I design rubrics,

▎ test prompts, and document failure cases; available 20+ hours/week (UTC+8)

I designed a 15-prompt evaluation study of DeepSeek V4 Flash, scoring historical accuracy, persona consistency, language style, plot logic, emotional depth, and concreteness. I documented failure modes and wrote a structured report with examples and recommendations.

I also built a 38KB Chinese narrative rule system with character cards, a decision ledger, and a collocation list. Its iterative QA process produced a narrative corpus and a reusable character-consistency rubric.

In other independent projects, I evaluated AI tools and researched historical texts, including writing two Chinese essays with source cross-checking. I’m a native Chinese speaker and can read technical documentation and follow English instructions.

Experience

Work history, roles, and key accomplishments

AI Product Evaluator

Payoneer

Evaluated AI-generated text and designed scoring rubrics for simplified Chinese, including a 38KB narrative rule system and a 15-prompt evaluation study of DeepSeek V4 Flash.

AI Output Evaluation Rubric Design Chinese Language Quality Review Prompt Testing Data Annotation QA Structured Feedback