Kenzo Tsunekawa
Machine Learning Engineer at Woven by Toyota
Chiyoda, Japan
Summary
🤩
Rockstar🎓
Top SchoolKenzo Tsunekawa is a machine learning engineer with 10 years of experience specializing in robotics, computer vision, and ML for autonomous systems. Currently at Woven by Toyota after shaping perception stacks at Tier IV, he has hands-on expertise improving lidar-based detection—most notably contributing a yaw normalization filter and per-class thresholding to the widely used Autoware.Universe project. His background spans research and industry, from multi-agent RL and language-evolution internships at Sony CSL to R&D in mining automation and robotics research at Universidad de Chile. Trained in Mechano-Informatics at The University of Tokyo and with a hardware-savvy B.Sc. from Universidad de Chile, he blends algorithmic depth with systems-level engineering. Kenzo is comfortable productionizing single-frame, TF-free perception nodes and enjoys bridging academic ideas with deployable autonomy solutions.
10 years of coding experience
8 years of employment as a software developer
University of TokyoBachelor of Science (B.Sc.), Licenciatura en Ciencias de la Ingeniería, Mención Eléctrica, Bachelor of Science (B.Sc.), Licenciatura en Ciencias de la Ingeniería, Mención Eléctrica at Universidad de Chile
English, Spanish, Japanese
Github Skills (10)
tensorrt10
cuda10
computer-vision10
c-language10
cprogramming-language10
ros10
autonomous-driving10
machine-learning9
python8
3d-mapping7
Programming languages (6)
Github contributions (5)
autowarefoundation/autoware_universe
Sep 2022 - Dec 2022
Role in this project:
ML Engineer
ML EngineerContributions:468 reviews, 8 commits, 106 PRs in 3 months
Contributions summary:Kenzo significantly contributed to the perception stack of the Autoware.Universe project. Their work focused on enhancing the lidar_centerpoint module by implementing and integrating a yaw norm filter to improve object detection accuracy. They modified code to include per-class yaw thresholding and incorporated class remapping functionalities. Furthermore, the user updated the node to function correctly without TF dependency, providing single-frame detection capabilities.
autowareros23d-mapcalibrationros
tier4/CalibrationTools
Jul 2022 - Jan 2023
sensor calibration tools for autonomous driving and robotics
Contributions:652 reviews, 104 commits, 114 PRs in 6 months
autonomous-drivingautowarecalibrationcamera-calibrationcomputer-vision
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.