Kaiyu Shi
Algorithm Engineer at AISpeech Co., Ltd.
Minhang District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolKaiyu Shi is an algorithm engineer with 10 years of experience specializing in NLP, speech processing, and neural network signal processing, currently building distributed deep learning infrastructure and edge-optimized models at AISpeech in Shanghai. He has hands-on expertise in PyTorch and Kaldi-based training frameworks, low-bit quantization and binarization for ASICs, and compiler co-design for domain-specific accelerators. Kaiyu has experience improving memory efficiency for model-parallel training from an internship at Microsoft and brings a rare cross-disciplinary background from Materials Science to a CS master’s at Shanghai Jiao Tong University. Known for moving deep learning "from huge to tiny," he focuses on practical, production-ready solutions for on-device speech enhancement and microphone-array processing.
10 years of coding experience
1 year of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Shanghai Jiao Tong University
Github Skills (200)
hackmd10
python10
nearest-neighbors10
mlops10
deep-learning10
gpu10
profiling10
noise10
gpu-acceleration10
clustering10
markdown10
acceleration10
numpy10
nvidia-smi10
llmops10
Programming languages (11)
Github contributions (5)
Stonesjtu/Pytorch-NCE
Apr 2017 - Nov 2019
The Noise Contrastive Estimation for softmax output written in Pytorch
Contributions:205 commits, 9 PRs, 127 pushes in 2 years 6 months
pytorchcontrastiveestimationnoisesoftmax
Stonesjtu/pytorch-learning
Feb 2018 - Apr 2019
Contributions:14 commits, 5 pushes in 1 year 1 month
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.