Steven Toribio
Software Engineer at Google
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolSteven Toribio is a software engineer with seven years of experience specializing in on-device machine learning and TensorFlow ecosystems, currently contributing to TensorFlow Lite and LiteRT at Google in New York. He has hands-on expertise deploying ML to resource-constrained embedded targets—contributing kernel runner refinements, test frameworks, and debugging utilities to tflite-micro—and has improved Android hardware buffer and GPU delegate support in TensorFlow itself. A former TA and course developer in data science and algorithms, he brings clear technical communication and pedagogy to complex ML engineering problems. His work balances low-level systems thinking with practical tooling: adding flatbuffer schema changes and composite operator support to enable real-world ML deployment. Colleagues can expect a pragmatic engineer who pairs production-focused code contributions with thoughtful test coverage and in-code documentation.
7 years of coding experience
1 year of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Washington University in St. Louis
English, Spanish
Github Skills (12)
machine-learning10
c-language10
tensorflow10
cprogramming-language10
android10
ml10
testing9
sys9
embedded9
gpu8
deep-learning7
python6
Programming languages (1)
Github contributions (5)
tensorflow/tflite-micro
May 2022 - Dec 2022
Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
Role in this project:
ML Engineer
ML EngineerContributions:81 reviews, 19 commits, 105 PRs in 7 months
Contributions summary:Steven primarily worked on enhancing the `tflite-micro` repository, which focuses on deploying ML models to embedded targets. Their commits demonstrate a focus on refining the kernel runner and related APIs within the project. The user's contributions are centered around adding test cases for the Tranpose Conv operation, fixing integration tests and improving the testing framework. They were also responsible for adding new functions, such as "PrintNBytes" to improve debugging and added in-code documentation.
signalml-modelslow-powerprocessorsdeployment
tensorflow/tensorflow
Mar 2025 - Mar 2025
An Open Source Machine Learning Framework for Everyone
Role in this project:ML Engineer
ML EngineerContributions:2 reviews, 1 PR in 2 days
Contributions summary:Steven primarily contributed to enhancing TensorFlow's capabilities, specifically related to Android hardware buffer support and GPU delegate improvements. Their work involved adding optional support for Android Hardware Buffers, enabling their use in TensorFlow Lite, and incorporating related test cases. Additionally, they made changes to the flatbuffer schema to support composite operators and updated build files to allow visibility, improving compatibility and functionality within the framework. The user also contributed to MHLO While legalization.
pythondata-sciencedeep-learningmlmachine-learning
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.