Cheney Zhang
Algorithm Engineer at Zilliz
Hangzhou City, Zhejiang, China
Summary
🤩
Rockstar🎓
Top SchoolCheney Zhang is an algorithm engineer with nine years of experience building production AI systems and extending vector search ecosystems from Hangzhou. At Zilliz he drove Milvus adoption by building integrations like DeepSearcher, langchain-milvus, and milvus-haystack that enable agentic RAG, graph RAG, and hybrid retrieval workflows. Previously he architected CMB’s enterprise AI platform and deployed OCR and document-recognition pipelines that significantly improved operational efficiency. Cheney is an active open-source contributor—authoring core modules for DeepSearcher and implementing clip4clip text–video retrieval examples—bridging research ideas and usable developer tools. He holds a master’s in Software Engineering from Nanjing University of Aeronautics and Astronautics and focuses on pragmatic vector-database applications across the AI stack.
9 years of coding experience
3 years of employment as a software developer
Master's degree, Computer Software Engineering, Master's degree, Computer Software Engineering at Nanjing University of Aeronautics and Astronautics
Github Skills (16)
machine-learning10
lm10
vector-database10
retrieval-augmented-generation10
embedding10
large-language-models10
python10
retrieval-augmented10
llm10
milvus9
image-classification9
jupyter-notebook9
nlp9
deep-learning9
pytorch8
Programming languages (8)
Github contributions (5)
towhee-io/examples
May 2022 - Jan 2023
Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.
Role in this project:
ML Engineer
ML EngineerContributions:28 commits, 41 PRs, 1 push in 7 months
Contributions summary:Cheney implemented the `clip4clip` functionality, which likely involves video-to-text or text-to-video retrieval. They worked on modifying and repairing a notebook focused on building a text-video retrieval engine. Their contributions included changes to image sizes and other notebook repair actions.
pythonimage-classificationunstructured-datareverse-image-searchvideo
zilliztech/deep-searcher
Feb 2025 - Apr 2025
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Role in this project:Back-end Developer
Back-end DeveloperContributions:1 release, 2 reviews, 59 PRs in 1 month
Contributions summary:Cheney initiated the framework for a deep research alternative, implementing core functionalities for online querying and offline data loading. They focused on developing agent-based features, specifically implementing sub-query generation and reflection mechanisms to enhance search capabilities. The user also introduced essential modules for file loading from local files and websites, demonstrating proficiency in setting up the project's foundational structure and integrating key functionalities.
agentagentic-ragclaudedeep-researchdeepseek
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.