Zhenyang Chen
高级开发工程师 at 蚂蚁金服
Minhang District, Shanghai, China
Summary
👤
Senior🎓
Top SchoolZhenyang Chen is a senior software engineer with nine years of experience building deep learning inference engines and secure hardware-backed services across Intel, OPPO Research, and Ant Financial. He specializes in fast deployment of ML models for edge and video systems, having developed an inference library at Intel and contributed production-ready speaker verification features to the open-source WeSpeaker toolkit. At Ant Financial he focuses on low-level security software and hardware integration—delivering TPM, TLS offload, and cryptographic services that blend national and international standards. Trained in integrated circuits at Shanghai Jiao Tong University, he uniquely bridges silicon-aware engineering with applied machine learning for mobile and enterprise products. Colleagues rely on him for pragmatic, performance-conscious solutions that move research prototypes into robust production.
8 years of coding experience
4 years of employment as a software developer
Master's degree, Engineering of integrated circuits, Master's degree, Engineering of integrated circuits at Shanghai Jiao Tong University
English
Github Skills (11)
pytorch10
machine-learning10
trainings10
data-augmentation10
python10
speaker-recognition10
speaker-verification10
modeling10
metric9
evaluation9
cosine-similarity9
Programming languages (3)
Github contributions (5)
wenet-e2e/wespeaker
Jan 2022 - Nov 2022
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Role in this project:
ML Engineer
ML EngineerContributions:36 reviews, 16 commits, 65 PRs in 10 months
Contributions summary:Zhenyang made several contributions related to speaker verification and recognition within the WeSpeaker toolkit. They implemented speed perturbation as a data augmentation technique, modifying the dataset loading and training scripts to incorporate it. Additionally, the user added a Python scoring script and integrated it into the training pipeline, demonstrating an understanding of model evaluation and performance metrics specific to speaker recognition tasks. They also worked on the automatic mixed precision training and fixed diarization bugs.
pythonproduction-readyecapa-tdnnspeaker-verificationproduction
czy97/czy97.github.io
Mar 2019 - Sep 2024
Contributions:124 pushes, 1 branch in 5 years 6 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.