Summary
Guilherme Potje is a Senior Applied Scientist with over a decade of research and engineering experience at the intersection of computer vision, machine learning and 3D perception, now building applied AI at Microsoft from Minas Gerais, Brazil. He combines a strong academic foundation—a PhD focused on local image features and efficient image matching—with hands-on systems work spanning C++, Python, embedded deployment, ROS, and large-scale camera stream processing. His career includes real-world R&D projects such as autonomous cavity exploration and HoloLens visualization, as well as industrial-grade pipelines for 3D reconstruction and SLAM used in robotics and aerial mapping. Comfortable moving from classical image processing to deep learning and LLM/LVM/SLM interests, he is adept at turning novel research into deployable systems and prototyping rapidly with tools like OpenCV, Open3D and PyTorch. A less obvious strength is his breadth across sensor modalities—RGB, RGB-D, LiDAR and multispectral—which enables robust multimodal perception solutions.
10 years of coding experience
11 years of employment as a software developer
PhD Computer Vision and Machine Learning, PhD Computer Vision and Machine Learning at Universidade Federal de Minas Gerais
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Universidade do Oeste Paulista
Portuguese, English