Guanxin Qiao
Software Engineer at Citadel Securities
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolGuanxin Qiao is a software engineer with six years of experience building large-scale machine learning serving systems and production ML infrastructure in the San Francisco Bay Area. He has driven model-serving features at Google, contributed remote predict RPC abstractions and unit tests to the widely used tensorflow/serving project, and worked on ML platforms at AWS and low-level CUDA libraries during an NVIDIA internship. Currently at Citadel Securities, he brings a background spanning computer vision and augmented reality at DiDi to high-performance, reliable inference pipelines. Guanxin combines systems-level thinking with practical engineering—comfortable modifying RPC protocols, writing robust unit tests, and optimizing for latency and throughput. His academic training from UIUC in computer engineering underpins a pragmatic approach to turning research-grade models into production services. Colleagues would note his mix of deep ML systems expertise and attention to software reliability that surfaces in both open-source and enterprise settings.
6 years of coding experience
5 years of employment as a software developer
Master Computer Engineering, Master Computer Engineering at University of Illinois Urbana-Champaign
English, Chinese
Github Skills (7)
machine-learning10
cpp10
tensorflow10
grpc9
deeplearning-ai9
deep-learning9
python5
Programming languages (1)
Github contributions (5)
tensorflow/serving
Aug 2020 - Sep 2022
A flexible, high-performance serving system for machine learning models
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 3 reviews, 28 commits in 2 years 1 month
Contributions summary:Guanxin primarily contributes to the `tensorflow/serving` repository, which is a system for serving machine learning models. Their contributions focus on implementing functionalities within the remote predict op, including abstracting RPC protocols. The user has also added unit tests for this feature, showcasing expertise in ensuring the reliability of model serving infrastructure. This indicates a focus on enhancing the serving capabilities for remote model inference.
cpppythonservingdeep-learningml
guanxinq/incubator-mxnet
Jan 2020 - Mar 2020
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Contributions:46 pushes, 11 branches in 2 months
pythonschedulerdataflowmutationorchestration
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.