Yin-chen Liao
Senior Software Engineer at uTensor (Open Source Neural Network Library for Microcontroller)
New Taipei, Taiwan
Summary
🤩
Rockstar🎓
Top SchoolYin-chen Liao is a Senior Software Engineer with 11 years of experience specializing in embedded ML and full-stack AI systems engineering. He has driven TinyML development as a core contributor to uTensor—building a Python code generator and implementing optimized C++ kernels to run neural networks on microcontrollers—and continues to contribute low-level ML operators and quantized inference improvements. His background spans robotics, recommendation systems, and cross-platform SDKs, combining C/C++, Python, and ML model deployment to deliver production-ready solutions. Based in New Taipei, Taiwan, he blends academic rigor from NTU with hands-on product engineering at companies like Coretronic, Pinkoi, and Empathia, and often focuses on squeezing performance out of constrained hardware rather than chasing model complexity.
11 years of coding experience
7 years of employment as a software developer
Master's degree, Economics, Master's degree, Economics at National Taiwan University
Stackoverflow
26reputation
209reached
1answer
0questions
Github Skills (16)
embedded10
machine-learning10
c-language10
deep-learning10
tensorflow10
cprogramming-language10
microcontroller10
sys10
neural-network9
convolutional-neural-networks9
cortex-m9
quantization8
pandas6
anaconda6
plot6
Programming languages (11)
Github contributions (5)
uTensor/uTensor
Dec 2017 - Jun 2021
TinyML AI inference library
Role in this project:
ML Engineer & Embedded Systems Engineer
ML Engineer & Embedded Systems EngineerContributions:16 reviews, 202 commits, 54 PRs in 3 years 6 months
Contributions summary:Yin-chen primarily worked on implementing and modifying machine learning operators for the `utensor` library, a TinyML AI inference library. Their contributions include adding convolution wrappers, addressing source code typos, updating include paths, fixing and refactoring the quantized convolution operator, and integrating max pooling operations. They also made improvements related to data types. Their work involved modifying the core functionality of the library and the related math libraries, targeting embedded systems with machine learning models.
pytorchiot-middlewareedge-computingdeep-learningtinyml
dboyliao/RBasic_Revised
Aug 2014 - Feb 2015
Contributions:87 commits, 2 branches in 5 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.