Peng Ye
Senior Staff Software Engineer, TLM at Uber
United States
Summary
🤩
Rockstar🎓
Top SchoolPeng Ye is a Senior Staff Software Engineer with 11 years of experience leading ML-driven products and data platforms at top-tier marketplaces like Uber and Airbnb. As Eng Lead of UberEats Feed Intelligence, he shapes recommendation and discovery experiences that materially drive orders, while his prior Airbnb roles combined ML research, forecasting, and platform engineering to surface reliable marketplace insights. He pairs deep academic training in electrical engineering (Tsinghua, Delaware, Maryland PhD) with hands-on contributions to open-source ML tooling—evidenced by back-end and model-evaluation work on Airbnb’s aerosolve project. Comfortable moving between model research, production systems, and team leadership, he focuses on model persistence, evaluation, and scalable data infrastructure. Colleagues rely on him to translate complex marketplace dynamics into robust, production-ready ML solutions.
11 years of coding experience
8 years of employment as a software developer
The University of Maryland, College ParkMS, Electrical Engineering, MS, Electrical Engineering at University of DelawareBE, Electrical Engineering, BE, Electrical Engineering at Tsinghua University
English, Chinese
Github Skills (8)
javas10
machine-learning10
java10
evaluation9
eval9
scala8
modeling8
trainings8
Programming languages (2)
Github contributions (3)
airbnb/aerosolve
May 2015 - Dec 2018
A machine learning package built for humans.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:166 commits, 88 PRs, 147 pushes in 3 years 7 months
Contributions summary:Peng contributed to the `aerosolve` machine learning package by implementing and testing core features. Their work included adding saving functionality to the `LinearModelTest` and creating a `testSave` method, demonstrating a focus on model persistence. Furthermore, the user modified the AUC (Area Under the Curve) computation and fixed a test failure, indicating involvement in model evaluation and performance optimization. They also added a new demo, demonstrating the income prediction functionality.
for-humanspythonmachine-learningdata-science
deerzq/Unsupervised-multi-metric-fusion-for-FR-IQA
Jul 2014 - Jul 2014
Contributions:5 commits, 1 comment, 1 issue in 2 days
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.