Sean Sheng
Director Of Engineering at Modular
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolSean Sheng is a seasoned engineering leader with 11 years of experience building high-throughput, distributed systems and AI infrastructure from edge to cloud. Currently Director of Engineering at Modular after serving as CTO of BentoML, he blends hands‑on backend and MLOps expertise with product and platform strategy to ship scalable inference and deployment tooling. His open-source contributions include meaningful enhancements to BentoML (advanced logging, dependency injection, adaptive batching) and core HTTP/2 improvements to LinkedIn’s Rest.li, reflecting deep experience in service infrastructure and performance-sensitive networking. Based in San Francisco, he has a track record of moving large systems from monoliths to service-oriented architectures and optimizing for production reliability at internet scale. Notably, he pairs low-level systems thinking—down to multiprocessing and marshal server tweaks—with leadership that aligns hardware, software, and cloud needs for modern AI workloads.
11 years of coding experience
15 years of employment as a software developer
Bachelor of Computer Science Computer Science, Bachelor of Computer Science Computer Science at University of Waterloo
Github Skills (22)
api-rest10
python10
back-end-development10
api-design10
restful-api10
configuration-management10
http10
java10
javas10
mlops10
yaml10
rest-api10
logging10
dependency-injection10
async9
Programming languages (11)
Github contributions (5)
linkedin/rest.li
Feb 2015 - Jun 2020
Rest.li is a REST+JSON framework for building robust, scalable service architectures using dynamic discovery and simple asynchronous APIs.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:10 reviews, 134 commits, 6 PRs in 5 years 5 months
Contributions summary:Sean primarily contributed to the back-end logic of the Rest.li framework, focusing on improving its HTTP/2 implementation and core components. Their work involved fixing bugs related to request handling, specifically when dealing with cookies and content length. They also refactored components, enhanced error handling, and implemented a host override list feature to improve D2.
architecturesapiscalableasynchronousrestful
bentoml/BentoML
Jan 2021 - Jan 2023
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Role in this project:Back-end Developer & MLOps Engineer
Back-end Developer & MLOps EngineerContributions:33 releases, 590 reviews, 68 commits in 2 years
Contributions summary:Sean focused on enhancing the logging capabilities of the BentoML framework, allowing for custom logging configurations via YAML. They implemented changes to allow for advanced customization by enabling logging configuration via a YAML file and configuring the file structure. The user also refactored code related to multiprocessing and made updates to the marshal server configuration. Furthermore, they introduced dependency injection, configuration revamp, and implemented improvements to the overall service, including logging formats and adaptive batching.
llm-inferencepythonmodel-deploymentaws-lambdaml-infrastructure
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.