Rodrigo De Andrade
Gestor De Desenvolvimento Em Machine Learning at Bosch
Paraná, Brazil
Summary
👤
Senior🎓
Top SchoolRodrigo De Andrade is a machine learning development manager and co-founder with nine years of experience building computer vision and deep learning solutions across industry and startups. Based in Paraná, Brazil, he currently leads ML development at Bosch while also driving product and engineering as CTO of Fresco Labs, an AI startup focused on reducing fresh food waste. Rodrigo's background spans hands-on Python, OpenCV and TensorFlow/Keras work, C++ for high-performance vision systems, and embedded mechatronics—skills backed by a master's in computer vision and ML. He contributes to notable open-source projects such as keras-retinanet and deepface, where his optimizations and model integrations improved performance and expanded model support. Known for turning PoCs into production-ready components, he blends research-informed approaches with pragmatic engineering to deliver measurable impact. An unusual strength is his cross-domain fluency from microcontroller prototyping to large-scale ML pipelines, enabling end-to-end ownership of vision-driven products.
10 years of coding experience
Pós graduação Especialização em Sistemas Embarcados para a Indústria Automotiva, Pós graduação Especialização em Sistemas Embarcados para a Indústria Automotiva at Federal University of Technology - ParanaPontifical Catholic University of Paraná
Portuguese, English
Github Skills (12)
object-detection10
keras10
computer-vision10
opencv10
machine-learning10
python10
face-recognition10
numpy10
retinanet9
jupyter-notebook8
onnx8
emotion-recognition3
Programming languages (7)
Github contributions (5)
fizyr/keras-retinanet
Apr 2018 - Apr 2018
Keras implementation of RetinaNet object detection.
Role in this project:
ML Engineer
ML EngineerContributions:5 commits, 2 PRs, 13 comments in 12 days
Contributions summary:Rodrigo significantly improved the speed of bounding box drawing in the RetinaNet implementation, achieving a substantial performance increase. The user also addressed a bug in the notebook view and implemented changes to incorporate image size parameters. In addition, the user introduced an elegant solution provided by another contributor.
kerasobject-detectionretinanet
serengil/deepface
May 2022 - May 2022
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Role in this project:ML Engineer
ML EngineerContributions:6 commits, 1 PR in 1 day
Contributions summary:Rodrigo implemented integration for a new face recognition model, SFace, into the deepface library. This involved creating wrapper classes for the SFace model from OpenCV, including loading weights and preprocessing images. Further contributions included adapting existing codebase to utilize the OpenCV preprocessing pipeline and fixing a shape mismatch.
face-recognitionpythonvgg-facefacenetopenface
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.