Kelton Zhang
Member Of Technical Staff at Fastino
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKelton Zhang is a software engineer with seven years of experience building AI-first backend systems and cloud-native tooling, currently based in San Francisco. He has shipped production LLM+RAG applications and inference platforms, driven ML/data pipelines and cloud cost optimization, and contributed to the popular open-source multimodal search framework Jina (notably refactoring batching and async client behavior). As a founding engineer at a YC company and a lead engineer at a Tsinghua spinoff, he blends startup velocity with research-driven rigor and holds an ECE Master's from Carnegie Mellon. Kelton’s work spans from low-latency backend refactors to hybrid semantic+SQL retrieval and practical RAG evaluation (patent-pending), showing a pattern of turning experimental models into reliable services.
7 years of coding experience
6 years of employment as a software developer
Master's degree Electrical and Computer Engineering, Master's degree Electrical and Computer Engineering at Carnegie Mellon University
Github Skills (26)
fastapi10
batching10
python10
indexing10
data-structure10
asyncio10
deep-learning10
executor10
file-handling10
data-structures10
jina10
batch10
application-framework9
machine-learning9
app-framework9
Programming languages (9)
Github contributions (5)
jina-ai/examples
May 2021 - Jul 2021
Jina examples and demos to help you get started
Role in this project:
Back-end Developer
Back-end DeveloperContributions:31 reviews, 51 commits, 8 PRs in 2 months
Contributions summary:Kelton implemented features related to compound indexers in the wikipedia-sentences example. Their work involved modifications to `app.py`, `executor.py`, and `indexer.py`, which included file handling, reading, writing and searching using these indexers. They also worked on making the application run by opening and reading lines of the toy wiki text. This involved file operations and restructuring parts of the code.
nlppythononboardingget-starteddeep-learning
jina-ai/serve
Mar 2021 - Jul 2021
☁️ Build multimodal AI applications with cloud-native stack
Role in this project:Backend Developer
Backend DeveloperContributions:9 reviews, 36 commits, 18 PRs in 3 months
Contributions summary:Kelton contributed to the refactoring of batching decorators within the `jina-ai/serve` repository. This involved modifying the `batching` decorator in `jina/executors/decorators.py` and associated unit tests. Additionally, the user addressed issues in the async client, modifying return types for asynchronous functions. These contributions suggest a focus on improving the performance and stability of the backend components.
opentelemetryllm-inferencecreative-aigrpcproduction
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.