Alexander Becker
PhD Candidate
Zurich, Zurich, Switzerland
Summary
🤩
RockstarAlexander Becker is a PhD candidate at ETH Zurich with eight years of software engineering experience focused on machine learning and multi-object tracking. He has hands-on expertise implementing and optimizing tracking systems—contributing motion-model adjustments, re-identification features, and performance-minded code cleanup to notable open-source work like "tracking_wo_bnw." Based in Zurich, he blends academic research rigor with production-oriented engineering, improving feature caching and alignment strategies to boost detection and tracking reliability. Colleagues can expect a practitioner comfortable moving between research prototypes and efficient, maintainable codebases. An understated strength is his ability to translate complex tracking research into pragmatic engineering improvements that measurably enhance system performance.
8 years of coding experience
Github Skills (8)
object-tracking10
computer-vision10
pytorch10
machine-learning10
python10
deep-learning9
algorithm9
algorithms9
Programming languages (4)
Github contributions (5)
phil-bergmann/tracking_wo_bnw
Oct 2019 - Feb 2020
Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"
Role in this project:
ML Engineer
ML EngineerContributions:5 commits, 2 PRs in 3 months
Contributions summary:Alexander primarily contributed to the implementation and refinement of a multi-object tracking system. Their work involved modifying the motion model, aligning object positions, and integrating features for re-identification within the tracking framework. They also made code cleanup and optimization changes, which likely improved the system's performance. Moreover, the user has added feature caching to enhance object detection.
object-detectiontrackingmulti-object-trackingbells-and-whistlesmulti-object
alebeck/boring
Oct 2024 - Mar 2025
The `boring` SSH tunnel manager
Contributions:2 PRs, 88 pushes, 2 branches in 5 months
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.