Ahmet Ozlu is a Staff Data Scientist with nine years of experience applying operations research and machine learning to large-scale optimization problems across telecom, retail, transportation, media, and hospitality. He specializes in supply chain, logistics, pricing optimization, and revenue management, bringing PhD-level rigor from Georgia Tech to drive data-informed business transformation. At companies including T-Mobile and Walmart he has led models that translate complex operational constraints into production-ready decision tools. He also contributes open-source computer vision work—most notably on a TensorFlow Object Counting API and vehicle-counting projects—demonstrating practical expertise in object detection, tracking, and applied CV pipelines. Based in Brussels, he blends academic depth with hands-on engineering, often bridging optimization theory and real-time ML systems to deliver measurable commercial impact.
9 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Industrial Engineering, Doctor of Philosophy (Ph.D.), Industrial Engineering at Georgia Institute of Technology
Bachelor’s Degree, Industrial Engineering, Bachelor’s Degree, Industrial Engineering at Bilkent University
:oncoming_automobile: "MORE THAN VEHICLE COUNTING!" This project provides prediction for speed, color and size of the vehicles with TensorFlow Object Counting API.
Role in this project:
ML Engineer & Data Scientist
Contributions:73 commits, 3 PRs, 70 pushes in 3 years 8 months
Contributions summary:Ahmet primarily contributed to vehicle detection and related functionalities within the repository. Their work involved integrating color recognition and speed prediction modules into the existing vehicle detection pipeline, likely using the TensorFlow Object Detection API. These changes included modifying the visualization utils and main detection script, indicating a focus on improving the project's core features, potentially including the integration of new models and improving the information displayed during inference. This implies a strong understanding of computer vision and machine learning principles.
🚀 The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems!
Role in this project:
Back-end Developer & ML Engineer
Contributions:1 release, 144 commits, 6 PRs in 3 years 3 months
Contributions summary:Ahmet appears to be contributing to the TensorFlow Object Counting API by adding and refactoring code related to the object detection pipeline and the associated visualization utilities. They are involved in integrating object tracking features and potentially improving the accuracy of object counting. Their work includes modifying the core API and utilizing libraries such as OpenCV for image processing and visualization.
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.