Yudong Cai
Full-stack Developer at Zilliz
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYudong Cai is a seasoned full-stack developer based in Shanghai with over a decade of C/C++ experience and seven years in large-scale software engineering across embedded systems, EDA, and network infrastructure. He helped build Milvus and its core vector engine Knowhere from the ground up at Zilliz, contributing backend performance improvements and SDK reliability for a high-profile open-source vector database. Prior roles at Cadence, Cisco, Synopsys and Samsung show deep expertise in emulation, HA/ISSU, data-structure optimization and ARM-based embedded multimedia development. Comfortable across C/C++, Python, scripting languages and Linux, he blends low-level performance tuning with practical system design. A high-achieving Zhejiang University alumnus, he’s as likely to optimize memory layout or expression parsing as to design cross-version compatibility mechanisms.
7 years of coding experience
13 years of employment as a software developer
M.Eng., Circuit and System, 1/112, GPA: 3.85, M.Eng., Circuit and System, 1/112, GPA: 3.85 at Zhejiang University
Chinese, English
Stackoverflow
19reputation
186reached
0answers
1question
Github Skills (18)
python10
milvus10
go10
sdk10
protobuffer10
protobuf10
data-management9
databases9
database9
dataframes8
dataframe8
vector7
documentation7
vector-math7
bioinformatics6
Programming languages (8)
Github contributions (5)
milvus-io/milvus
Apr 2020 - Jan 2023
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Role in this project:
Back-end Developer
Back-end DeveloperContributions:237 reviews, 507 commits, 862 PRs in 2 years 9 months
Contributions summary:The user, cai.zhang, appears to be a back-end developer focusing on building and maintaining core functionality within the Milvus project. They implemented an indexbuilder client and added interfaces for index creation in the proto files. The user's commits focus on optimizing the code, including changes to reduce memory consumption and improve expression parsing efficiency, suggesting a focus on code performance. They also contributed to tests, enhancing the overall reliability of the index components.
approximate-nearest-neighbor-searchfaisshnswsimilarity-searchvector
milvus-io/pymilvus
Apr 2021 - Nov 2022
Python SDK for Milvus.
Role in this project:Back-end Developer
Back-end DeveloperContributions:19 reviews, 109 commits, 74 PRs in 1 year 6 months
Contributions summary:Yudong primarily focused on implementing and refining the core functionalities of the `pymilvus-io` Python SDK. Their work included adding and modifying methods related to the collection properties. They also added examples and documentation to showcase how to use the `Collection` class. Additionally, they fixed bugs in the code related to primary key fields, dataframe insertion, and auto_id functionality.
pythonsdkannsdatabasevector
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.