For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
X
Xiang Li

Xiang Li

AI Model Trainer & Prompt Engineer | Alignerr

Japan flagN/A, Japan
$15.00/hrIntermediateAws SagemakerCVATRoboflow

Key Skills

Software

AWS SageMakerAWS SageMaker
CVATCVAT
RoboflowRoboflow
LabelboxLabelbox

Top Subject Matter

Multilingual AI training
LLM evaluation
PII annotation

Top Data Types

ImageImage
TextText
VideoVideo
AudioAudio
DocumentDocument

Top Task Types

PolygonPolygon
Question AnsweringQuestion Answering
Text GenerationText Generation
Text SummarizationText Summarization
Translation/LocalizationTranslation/Localization
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

AI Model Trainer & Prompt Engineer | Alignerr. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Labelbox. Education includes Bachelor of Engineering, Shanghai University of Engineering Science (2018) and Research Student, Okayama University (2019). AI-training focus includes data types such as Text and labeling workflows including Prompt + Response Writing (SFT).

IntermediateJapaneseChinese MandarinHebrewGermanEnglish

Labeling Experience

Labelbox

AI Model Trainer & Prompt Engineer | Alignerr

LabelboxTextPrompt Response Writing SFT
In this role, I designed and evaluated multilingual prompts for large language models using Labelbox and proprietary Labeling Studio. I conducted structured scoring of AI-generated audio and text outputs, annotated PII in datasets, and performed validation and compliance testing to enhance model reliability. I also reviewed AI-generated code and assessed e-commerce conversational AI outputs for various quality metrics. • Developed and iterated prompts in English, Japanese, and Chinese for LLM improvement. • Performed audio evaluation focusing on tone, emotion, pronunciation, and CER/WER transcription errors. • Executed PII annotation in multilingual datasets to ensure regulatory compliance. • Assessed conversational AI outputs for readability, relevance, and classification accuracy.

In this role, I designed and evaluated multilingual prompts for large language models using Labelbox and proprietary Labeling Studio. I conducted structured scoring of AI-generated audio and text outputs, annotated PII in datasets, and performed validation and compliance testing to enhance model reliability. I also reviewed AI-generated code and assessed e-commerce conversational AI outputs for various quality metrics. • Developed and iterated prompts in English, Japanese, and Chinese for LLM improvement. • Performed audio evaluation focusing on tone, emotion, pronunciation, and CER/WER transcription errors. • Executed PII annotation in multilingual datasets to ensure regulatory compliance. • Assessed conversational AI outputs for readability, relevance, and classification accuracy.

2024 - Present

Education

T

The University of Osaka

Ph.D., Materials science and engineering

Ph.D.
2022 - 2024
K

Kansai University

Master's in Engineering, Material Engineering

Master's in Engineering
2020 - 2022

Work History

K

Kolabtree

Research Consultant

N/A
2024 - Present
O

Osaka University

Ph.D. Candidate and Teaching Fellow

Osaka
2022 - Present