Yao Weng is a software engineer with nine years of experience building scalable data and ML infrastructure at Bloomberg in New York, currently contributing to the Data Science Platform. Trained as a physicist with a Ph.D. from Cornell, he brings a researcher's rigor to production engineering, specializing in real-time analytics and model-serving workflows. His open-source work on kserve highlights practical MLOps expertise—improving storage tests, multi-model configuration, and model load/unload endpoints to harden Kubernetes-based inference. Comfortable across systems, testing, and dockerized deployments, he thrives on turning complex scientific and financial requirements into reliable, automated platforms.
9 years of coding experience
7 years of employment as a software developer
B.S, Physics, B.S, Physics at Central China Normal University
Standardized Serverless ML Inference Platform on Kubernetes
Role in this project:
MLOps Engineer
Contributions:7 reviews, 5 commits, 16 PRs in 8 months
Contributions summary:Yao primarily contributed to the configuration and deployment of machine learning models within the kserve/kserve platform. Their work included fixing storage tests related to minio, adding and modifying configuration maps for multi-model serving, and integrating load/unload endpoints for model management. They also updated testing procedures and docker configurations.
Envoy AI Gateway is an open source project for using Envoy Gateway to handle request traffic from application clients to Generative AI services.
Contributions:44 pushes, 6 branches in 3 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.