Open to opportunities

Ian Li

@ianli

Message

Bilingual AI practitioner who evaluates and improves multilingual LLM outputs through hands-on testing.

China

Message

What I'm looking for

I’m looking for remote, asynchronous work where I can use LLM tools to code and evaluate multilingual outputs. I want roles that value detail, strong written communication, and continuous improvement focused on accuracy, tone, and AI safety.

I’m a bilingual Chinese-English AI practitioner focused on evaluating, testing, and giving actionable feedback on large language model outputs. I’m meticulous about accuracy, fluency, and cultural appropriateness across both languages.

As a self-employed AI Tools Power User & Independent Developer (2024–present), I use Claude, ChatGPT, and Gemini daily for coding, research, and content work. I also build and maintain open-source projects on GitHub with AI-assisted development workflows, including multi-agent task delegation, output quality review, and error diagnosis.

I’m especially interested in AI safety, alignment, and the quality of multilingual AI outputs. In my workflow, I document and report software bugs with detailed reproduction steps, root cause analysis, and verification—so results are both correct and reproducible.

Experience

Work history, roles, and key accomplishments

Current

AI Tools Power User

Current

Self-Employed

Jan 2024 - Present (2 years 6 months)

Extensive daily use of Claude, ChatGPT, and Gemini for coding, research, and content. Evaluated AI outputs for accuracy, fluency, and cultural appropriateness, and built/maintained GitHub open-source projects using AI-assisted multi-agent workflows with quality review and error diagnosis.