Chen Cen
Machine Learning Engineer at stripe
California, United States
Summary
👤
SeniorChen Cen is a seasoned ML mobile engineer with 12 years of experience bringing state-of-the-art transformer models and on-device inference to production mobile apps. He helped design TensorFlow Lite Task APIs at Google and later built cross-platform mobile ML SDKs at Stripe—work that was featured at Google I/O—and now focuses on deploying SOTA models to resource-constrained devices at Argmax. His open-source contributions include implementing a BERT-based NLClassifier for TensorFlow Lite Support, adding Java APIs, tokenization, and robust tensor handling for mobile NLP. Comfortable across Android, iOS, React Native and native C++, Chen combines deep ML engineering with pragmatic SDK design, and has a track record of shipping infrastructure used by billions of devices.
13 years of coding experience
Github Skills (10)
tokenize10
machine-learning10
tokenizer10
nlp10
tensorflow-lite10
bert10
natural-language-processing10
java9
metadata9
javas9
Programming languages (3)
Github contributions (5)
tensorflow/tflite-support
Jul 2020 - Feb 2021
TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.
Role in this project:
ML Engineer
ML EngineerContributions:31 commits in 6 months
Contributions summary:Chen primarily contributed to the development of a Natural Language Classifier (NLClassifier) extension for Bert models within the TFLite support library. Their work involved creating new files, modifying existing ones to incorporate the new classifier, and implementing methods to preprocess and postprocess text data. The contributions included the addition of Java implementations and APIs for the BertNLClassifier, and involved tokenization, and also addressed the handling of various output tensor types (such as bool) in NLClassifier.
iot-devicemachine-learningmobiletflite
flamearrow/Bitemap
Feb 2015 - Jan 2016
Contributions:92 commits, 79 pushes, 1 branch in 10 months
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.