Bo Shao

Software Engineer at AECOM

Miami, Florida, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Bo Shao is a software engineer with a PhD in Computer Science and nine years of industry experience, currently building software at AECOM in Miami. He blends research-grade expertise in data mining and machine learning with practical backend engineering, evidenced by his contributions to an open-source TensorFlow seq2seq chatbot where he improved model accuracy with attention, dropout, GRUCells and bucketing. Comfortable merging research and production, he focuses on scalable architecture and model optimization while also smoothing user-facing interactions. His profile reflects a rare combination of academic depth and hands-on implementation that accelerates ML projects from prototype to deployable systems.
code9 years of coding experience
bookDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Florida International University
github-logo-circle

Github Skills (8)

attention-mechanism10
machine-learning10
tensorflow10
python10
seq2seq10
model-optimization10
data-augmentation9
nlp9

Programming languages (3)

C++Jupyter NotebookPython

Github contributions (5)

github-logo-circle
bshao001/ChatLearner

Jun 2017 - Mar 2019

A chatbot implemented in TensorFlow based on the seq2seq model, with certain rules integrated.
Role in this project:
userBack-end Developer & ML Engineer
Contributions:151 commits, 130 pushes, 4 branches in 1 year 9 months
Contributions summary:Bo made significant contributions to the chatbot's functionality, primarily by optimizing the user interface, including enabling a smooth exit. They were also involved in the model's architecture, by merging changes and integrating new features, such as the implementation of bucketing, and adding output projection to support a larger vocabulary. Furthermore, the user focused on enhancing the model's performance and accuracy by introducing dropout layers, GRUCell, and adding attention mechanism, including expanding the training data set, which involved both code modifications and model configuration.
nlpintegratedseq2seqseq2seq-modeltensorflow
Contributions:9 commits, 8 pushes, 1 branch in 8 days
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
Bo Shao - Software Engineer at AECOM