Sai Miryala
Machine Learning Engineer at Facebook
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolSai Miryala is a Machine Learning Engineer with seven years of experience building production ML systems across scale-driven companies including Facebook and Uber, and a background in research from Microsoft Research India and Bloomberg. He specializes in applied ML for risk prevention and conversational AI, with hands-on experience shipping voice assistant features and payment risk models. Sai contributes to prominent open-source ML tooling—helping maintain Ludwig’s integration tests and add features like image inputs and sequence combiners—demonstrating a strong focus on test quality and maintainability. Trained at IIT Kharagpur and Carnegie Mellon, he blends rigorous academic foundations with pragmatic engineering to move ML prototypes into reliable production.
7 years of coding experience
6 years of employment as a software developer
Dual Degree (B.Tech + M.Tech), Electrical Engineering (Spl. in Instrumentation Engineering), Dual Degree (B.Tech + M.Tech), Electrical Engineering (Spl. in Instrumentation Engineering) at Indian Institute of Technology, KharagpurMaster's degree, Intelligent Information Systems at LTI, School of Computer Science, Master's degree, Intelligent Information Systems at LTI, School of Computer Science at Carnegie Mellon University
English, Hindi, Spanish, Telugu
Github Skills (14)
integration-testing10
testing10
pytest10
python10
test-automation10
tensorflow9
deep-learning8
machine-learning8
nlp7
data-preprocessing7
computer-vision6
pytorch6
data-science6
llm5
Programming languages (1)
Github contributions (5)
ludwig-ai/ludwig
Jan 2019 - Dec 2019
Low-code framework for building custom LLMs, neural networks, and other AI models
Role in this project:
Back-end & QA Engineer
Back-end & QA EngineerContributions:74 commits, 37 PRs, 105 pushes in 11 months
Contributions summary:Sai primarily focused on updating and maintaining integration tests within the Ludwig framework. Their work involved refactoring test code, updating dependencies, ensuring PEP8 compliance, and removing dataset dependencies. They also introduced and tested new features, such as image input features, tied weights, and sequence combiners within the existing testing structure. These efforts demonstrate a clear commitment to maintaining code quality and comprehensive testing coverage.
fairness-mlpythonframework-learningdeep-learning-frameworknatural-language-processing
teeso/ludwig
May 2019 - May 2019
Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code.
Contributions:2 commits in 1 day
ludwigdeep-learningtoolboxmachine-learningdeep-learning-models
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.