[email protected]

Key Skills

Software

Data Annotation Tech

Datumbox

LightTag

Labelbox

Remotasks

Tagtog

Top Subject Matter

Education Technology

User Experience

Content Development

Top Data Types

Text

Document

Top Task Types

Emotion Recognition

Classification

Entity (NER) Classification

Point/Key Point

Text Generation

Question Answering

Text Summarization

Freelancer Overview

Product Manager – Feedback Analysis Automation (Spring of Sing). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Arts, 江南大学 (2020). AI-training focus includes data types such as Text and labeling workflows including Emotion Recognition, Classification, and Entity (NER) Classification.

Labeling Experience

Product Manager – Feedback Analysis Automation (Spring of Sing)

TextEmotion Recognition

Designed and implemented automated sentiment analysis and topic clustering systems for large-scale unstructured user feedback using LLMs. Developed multi-label classification strategies based on intent recognition to handle mixed-topic responses and ensured high coverage of key issues. Oversaw embedding AIGC capabilities and dynamic prompt templates into content development workflows for efficiency gains and enhanced content quality. • Leveraged intent recognition to surpass 85% coverage in identifying core issues. • Embedded LLM-driven emotion and topic analysis into operational feedback loops. • Utilized internal AI platforms like Accio for multimodal integration and rapid prototyping. • Established automated, scalable pipelines for feedback ingestion and annotation.

2022 - Present

Product Manager – Sales Process AI Assistance (Xiaozhi Project)

TextEntity (NER) Classification

Directed the design, deployment, and refinement of an automated system to extract, standardize, and annotate unstructured sales communications from sources like WeChat and calls. Implemented a hybrid chunking and sentence re-ranking strategy using RAG/BGE to optimize the construction and annotation of a high-accuracy sales conversation corpus. Developed entity and intent recognition workflows to classify, tag, and label sales records for knowledge-base creation and salesperson guidance. • Elevated template usability rates by more than 40% through improved annotation techniques. • Utilized Accio and Internal/Proprietary Tooling for rapid deployment and workflow design. • Piloted annotation effectiveness in a month-long trial with measurable time savings. • Established routines for AI-generated intent and entity feedback to inform sales SOPs.

2025 - 2026

Product Manager – AI Education Content Tool (Yinzhi Project)

TextClassification

Led the development of an AI-empowered lesson preparation engine using OCR and dynamic prompt engineering for rapid, structured curriculum generation. Managed the design and implementation of automated feedback sentiment and multi-label topic classification solutions using LLMs. Created a framework for “outline-key points-examples” structured output and factuality checks to standardize educational content. • Reduced content preparation time per lesson from 40 minutes to 10 minutes. • Achieved over 85% core issue coverage via intent-based multi-label classification. • Piloted internal multimodal AI integration on the Accio platform for agile productization. • Built automated feedback pipelines to improve content quality and instructional design.

2025 - 2025

Education

Work History