H2 H.

Key Skills

Software

AWS SageMaker

CloudFactory

Anno-Mage

Axiom AI

Top Subject Matter

Enterprise Knowledge Base

Private LLM Deployment

Intelligent Q&A

Top Data Types

Text

Document

Image

Top Task Types

Fine-tuning

Data Collection

Prompt + Response Writing (SFT)

Freelancer Overview

AI Application Engineer (Internship) - Model Fine-tuning and Knowledge Base Construction. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include FastGPT, FAISS, and Coze. Education includes Bachelor of Engineering, Guangdong Polytechnic Normal University (2026). AI-training focus includes data types such as Text and Document and labeling workflows including Fine-tuning, Data Collection, and Prompt + Response Writing (SFT).

Labeling Experience

AI Application Engineer (Internship) - Model Fine-tuning and Knowledge Base Construction

TextFine-tuning

Built and maintained an enterprise knowledge base using FastGPT, then performed targeted model fine-tuning to improve language model response relevance for specific business scenarios. Designed prompt templates and supervised the training process by curating and labeling relevant query-response pairs aligned with real business workflows. Integrated feedback loops, collecting and annotating conversational logs to further refine the model's output accuracy. • Developed prompt-response pairs for supervised fine-tuning. • Labeled conversational data for relevant, context-aware responses. • Used internal evaluation to review and correct model outputs. • Integrated labeling tasks with FastGPT and Dify tools.

2026 - Present

Software Development & AI Application Engineer (Internship) - Knowledge Base Curation

DocumentData Collection

Constructed a unified AI knowledge base by gathering and organizing diverse business documents, including process standards and quality control specifications. Performed intelligent document chunking, vectorization, and labeling to enable precise retrieval and automated reasoning for the company's decision agent. Regularly labeled data entities and key facts within these documents to support accurate real-time analysis. • Collected and split business documents for training and retrieval. • Performed data annotation and labeling for decision agent support. • Used FAISS and proprietary tools to vectorize and store labeled data. • Maintained document updates and curated relevant content for model use.

2025 - 2026

AI Application Engineer (Internship) - Prompt/Response Annotation and RAG

TextPrompt + Response Writing (SFT)

Developed and annotated prompts and responses for agent-driven production scheduling and supply chain procurement workflows. Used Retrieval-Augmented Generation (RAG) to label and construct historical process libraries, enabling the AI agent to retrieve and recommend optimal solutions. Oversaw prompt quality, scenario relevance, and integrated user feedback for iterative improvement. • Crafted annotated prompts for training production scheduling agents. • Labeled and stored historical process data for retrieval tasks. • Evaluated and refined label quality based on live system output. • Used Coze and internal tools to manage prompt-response datasets.

2025 - 2025

Education

Work History