Quentin Khan
Software Engineer at Google
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolQuentin Khan is a software engineer based in Zurich with 10 years of experience focused on high-performance computing, optimized C/C++ routines, and ML inference. Currently at Google, he brings practical expertise from Agenium Scale and Inria where he developed low-latency image processing, FPGA inference advice, and adaptive Fast Multipole Method implementations. He has hands-on experience across system-level optimization, Qt GUIs, and backend Python/Vue teaching platforms, and is comfortable moving between research and production code. An active contributor to TensorFlow, he has improved TFLite stability and quantized model support—work that reflects his interest in making ML runtimes both faster and more reliable. Colleagues know him as an HPC enthusiast who enjoys solving tough problems and mentoring others while translating research ideas into deployable software.
10 years of coding experience
7 years of employment as a software developer
Master's Degree / Engineering Diploma, Computer Science, Master's Degree / Engineering Diploma, Computer Science at ENSEIRB-MATMECA
Github Skills (9)
c-language10
tensorflow-lite10
cprogramming-language10
testing9
machine-learning9
model-optimization8
tensorflow7
machine-learning-models6
ml-deployment6
Programming languages (6)
Github contributions (5)
tensorflow/tensorflow
Oct 2022 - Nov 2022
An Open Source Machine Learning Framework for Everyone
Role in this project:
ML Engineer
ML EngineerContributions:43 reviews, 9 commits, 3 PRs in 1 month
Contributions summary:Quentin made several changes related to the TensorFlow Lite (TFLite) framework, specifically concerning weight caching, the `DILATE` operation, and StableHLO composite operations. They implemented and refined testing for `stablehlo.reduce_window` and made contributions towards processing model graphs by modifying the graph partitioning processes and improving the accuracy and stability of the TFLite model format. Their contributions include both adding and testing new features and fixing bugs, particularly with regards to the XNNPack delegate and quantized models.
pythondata-sciencedeep-learningmlmachine-learning
xaxousis/bash-params
Jul 2015 - Feb 2019
Contributions:6 pushes, 1 branch in 3 years 7 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.