Binbin Zhang - Operations Manager

Binbin Zhang

Operations Manager

Arcadia, California, United States

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Binbin Zhang is an operations-minded data analyst and manager with 11 years of cross-border e-commerce and analytics experience, currently leading operations and business systems for a global seller-facing company. She has deep expertise in shipping performance, seller policy design, trust & risk analytics, and building programs like certified warehouse networks and fraud containment at scale. Comfortable bridging data science, product and operations, Binbin pairs hands-on analytics with systems thinking to turn policy and model insights into operational workflows. She also contributes to open-source speech and speaker-recognition toolkits, improving core encoder/decoder components and data pipelines—an unusual blend of ML engineering and e-commerce operations. Trained in business analytics and economics, she brings both quantitative rigor and practical execution to growth and risk challenges.

11 years of coding experience

1 year of employment as a software developer

Bachelor's degree Business Administration , Bachelor's degree Business Administration at Tunghai University

Master of Science - MS Business Analytics , Master of Science - MS Business Analytics at Bentley University

Economics, Economics at Università Cattolica del Sacro Cuore

Chinese, English, hokkien, Italian

Github Skills (18)

deco10

pytorch10

python10

speaker-verification10

encoder10

data-engineering10

lmdb10

machine-learning10

decode10

decoding10

deep-learning10

speech-recognition10

decoder10

data-augmentation9

cuda9

Programming languages (3)

C++ShellPython

Github contributions (5)

wenet-e2e/wenet

Sep 2020 - Jan 2023

Production First and Production Ready End-to-End Speech Recognition Toolkit

Role in this project:

Back-end Developer

Contributions:6 releases, 1102 reviews, 738 commits in 2 years 4 months

Contributions summary:Binbin primarily contributed to the core functionality of the end-to-end speech recognition toolkit. Their work involved adding and refining encoder and decoder components, as well as implementing model export functionalities. They addressed and fixed bugs related to padding and masking, and improved the batch decoding capabilities. Furthermore, the user integrated the model with the libtorch and improved the model by optimizing its performance.

pytorchend-to-endasrproduction-readyspeech-to-text

wenet-e2e/wespeaker

Mar 2022 - Nov 2022

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

Role in this project:

Back-end Developer & MLOps Engineer

Contributions:49 reviews, 16 commits, 63 PRs in 8 months

Contributions summary:Binbin primarily worked on integrating LMDB for handling noise and reverb data augmentation and adding support for raw datasets. They modified the dataset processing pipeline, including `wespeaker/dataset/processor.py`, and updated the training script and configuration to incorporate these new data sources. Additionally, they introduced related tools like `make_lmdb.py` to convert wav files into an LMDB format, demonstrating a focus on data handling and pipeline enhancements for the speaker verification toolkit.

pythonproduction-readyecapa-tdnnspeaker-verificationproduction

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.

Request Free Trial