Linchen Xiao
Senior Algorithm Engineer at 蚂蚁集团
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolLinchen Xiao is a Senior Algorithm Engineer with nine years of experience building data-driven solutions across fintech and enterprise environments, currently driving algorithm development at Ant Group in Shanghai. With an academic foundation in telecommunications and information technology from RWTH Aachen and German universities, she blends strong engineering rigor with a practical Data Science mindset. She contributes to open-source AI tooling—most notably adding subjective evaluation and multi-backend integration to the popular OpenCompass LLM evaluation platform—demonstrating expertise in backend systems and model evaluation. Her background spans product-oriented roles at METRO.digital and METRONOM, plus hands-on data engineering at Vodafone, giving her a rare combination of research-quality modeling and production engineering. Colleagues describe her as someone who treats engineering as data’s best friend: pragmatic, detail-oriented, and focused on measurable impact.
9 years of coding experience
3 years of employment as a software developer
Bachelor of Science (B.Sc.), Information Technology, 1.9, Bachelor of Science (B.Sc.), Information Technology, 1.9 at Fachhochschule LübeckMaster of Science (MSc), Telecommunications Engineering, 1.5, Master of Science (MSc), Telecommunications Engineering, 1.5 at RWTH Aachen UniversityBachelor of Engineering (B.Eng.), Information Technology, 1.9, Bachelor of Engineering (B.Eng.), Information Technology, 1.9 at East China University of Science and Technology
German, English, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (10)
machine-learning10
lm10
evaluation-framework10
large-language-models10
python10
evaluation10
ml10
llm10
benchmarking9
benchmark9
Programming languages (1)
Github contributions (5)
open-compass/opencompass
Jul 2024 - Apr 2025
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:13 releases, 201 reviews, 256 PRs in 9 months
Contributions summary:Linchen primarily contributed to the development and integration of CompassBench v1.3 subjective evaluation. This involved adding new configurations for models, datasets and evaluators. The code changes include new Python scripts to handle the evaluation logic and integration with various LLM backends such as TurboMind. They also added a summarizer for analyzing subjective evaluation results.
benchmarkchatgptevaluationlarge-language-modelllama2
MaiziXiao/opencompass
Jul 2024 - Apr 2025
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Contributions:126 pushes, 93 branches in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.