Diego Fernández
Sr AI Engineer at Cometa
Montevideo, Montevideo, Uruguay
Summary
🤩
Rockstar🎓
Top SchoolDiego Fernández is a Sr AI Engineer based in Montevideo with five years of hands-on experience building and deploying machine learning systems. He progressed from Machine Learning Engineer to Lead ML Engineer and now leads AI efforts at Cometa, blending research-driven development with product-focused delivery. Diego has practical experience integrating object detection and real-time multi-object tracking, contributing demos and improvements to the popular tryolabs/norfair project using YOLOv7 and YOLOPv2. Trained in Ingeniería en Computación and fluent in English, he pairs solid academic grounding with clear technical communication. Colleagues describe him as someone who moves quickly from prototypes to polished demos, making complex vision models accessible through reproducible notebooks and scripts. He brings a pragmatic balance of open-source collaboration and production engineering to AI initiatives.
5 years of coding experience
4 years of employment as a software developer
Examination for the Certificate of Competency in English, Examination for the Certificate of Competency in English at University of MichiganIngeniería en Computación, Ingeniería en Computación at Universidad de la República
Github Skills (8)
multi-object-tracking10
object-detection10
computer-vision10
jupyter-notebook10
yolov710
python10
pytorch9
ffmpeg8
Programming languages (2)
Github contributions (5)
tryolabs/norfair
Sep 2022 - Jan 2023
Lightweight Python library for adding real-time multi-object tracking to any detector.
Role in this project:
ML Engineer
ML EngineerContributions:14 reviews, 16 commits, 11 PRs in 3 months
Contributions summary:Diego contributed to the project by adding a demo using a YOLOV7 model, specifically a Colab notebook, to showcase the object tracking features of the library. The user also made multiple updates to the demo, including fixing typos, improving the demo, and integrating a YOLOPv2 demo. These changes involved modifying existing Python scripts and Jupyter notebooks to integrate the object detection and tracking functionalities.
pythonre-idreal-timeobject-detectiondetector
tryolabs/soccer-video-analytics
Sep 2022 - Oct 2022
Demo on how to compute soccer ball possession automatically using AI.
Contributions:31 commits in 10 days
ball-possessioncamera-motionclassificationmulti-object-trackingnorfair
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.