Yan-ru Su
Research Engineer at ASUS
Singapore, Singapore
Summary
👤
Senior🎓
Top SchoolYan-ru Su is a research engineer based in Singapore with 10 years of experience building production-ready AI systems, specializing in computer vision, image segmentation, and video classification. She has led end-to-end efforts from research to deployment—creating an in-house deep learning framework at ASUS and integrating MLOps to accelerate experimentation and inference across prior roles. Her work spans practical product impact, from a fashion detection system with strong attribute accuracy to a 3.6x inference speedup in healthcare AI, and she consistently focuses on robustness and stability beyond demos. Comfortable with data pipelines and model serving (Airflow, Redash, recommender post-processing), she blends research publications and conference presentations with hands-on engineering. An understated detail: she has competed successfully in applied forecasting challenges, reflecting a knack for translating models into measurable business wins.
10 years of coding experience
2 years of employment as a software developer
碩士 Computer Science and Engineering, 碩士 Computer Science and Engineering at National Sun Yat-sen University
Github Skills (44)
pytorch10
filesystem10
openai-api10
data-science10
image-processing10
machine-learning10
vector-database10
cookiecutter10
multimodal10
large-language-models10
llm10
webui10
agent10
openai10
ai10
Programming languages (4)
Github contributions (5)
daniel-code/TubeViT
Jan 2023 - Mar 2023
An unofficial implementation of TubeViT in "Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning"
Contributions:75 commits, 21 PRs, 50 pushes in 1 month
paper-implementationspytorchvideo-classificationvittube-vit
daniel-code/dogs-cats-classifier
Oct 2022 - Nov 2022
Create an algorithm to distinguish dogs from cats
Contributions:3 releases, 40 PRs, 48 pushes in 23 days
kagglepythondeep-learningmachine-learningimage-classification
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.