Tingting Z.

Key Skills

Software

Scale AI

Top Subject Matter

LLM (Large Language Model) output evaluation and QA

Top Data Types

Image

Audio

Text

Top Task Types

Classification

Text Generation

Text Summarization

RLHF

Transcription

Evaluation/Rating

Function Calling

Freelancer Overview

I have been working as a Chinese QA specialist at Outlier for nearly 2 years, contributing to multiple AI training and evaluation projects across speech, image, RLHF, rubric design, and safety domains. Experienced in multilingual data quality review, prompt evaluation, annotation guideline interpretation, and improving model response quality and safety alignment.

Labeling Experience

Chinese QA Specialist (AI Model Evaluation) at Outlier (Remote)

Don't discloseText

Performed AI model evaluation by reviewing LLM outputs for quality and policy compliance. Provided structured, actionable feedback to improve prompt design and increase reliability of responses. Identified edge cases, inconsistencies, and hallucinations to strengthen model robustness. • Rated/assessed factual accuracy of generated content. • Assessed reasoning quality, safety, and instruction adherence. • Wrote structured feedback for prompt and response improvements. • Flagged issues such as hallucinations and inconsistencies.

2024 - Present

Education

Work History