Desmond Yao
Summary
🤩
RockstarJin Yao is a software engineer with 7 years of experience specializing in ML model optimization, low-bit quantization, and deployment acceleration. Based in Nanjing, he currently drives research and engineering in LLM quantization, ONNX optimization, and parallelism at Tsingmicro after building medical imaging and TensorRT acceleration expertise at JF Healthcare. His background includes FPGA prototyping and accelerator work from internships at Microsoft and Horizon Robotics, giving him a rare hardware-to-software perspective on performance engineering. He combines algorithmic work on quantization with practical converter and deployment tooling, enabling faster, lower-precision inference in production environments. Notably, he pairs solid academic roots from Beihang University with hands-on contributions across model optimization pipelines rather than just research prototypes.
7 years of coding experience
Github Skills (187)
transformers10
realtime10
emotion-recognition10
python10
deep-learning10
instance-segmentation10
gpu10
gemma10
arm10
quantization10
tflite10
gpu-acceleration10
glm10
optimization10
object-tracking10
Programming languages (9)
Github contributions (5)
inisis/ultralytics
May 2024 - Dec 2025
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
Contributions:38 pushes, 2 branches in 1 year 7 months
coremlonnxopenvinopytorchtflite
inisis/caffe2onnx
Sep 2021 - Nov 2022
caffe model to onnx
Contributions:66 commits, 1 PR, 62 pushes in 1 year 1 month
caffeonnx
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.