Nicolai Wojke
Staff AI Software Engineer at Tensordyne
Berlin, Germany
Summary
🤩
Rockstar🎓
Top SchoolNicolai Wojke is a Staff AI Software Engineer in Berlin with 9 years of experience building production-grade perception and tracking systems for automotive and robotics applications. He holds a PhD in computer vision and moved from academic multi-object tracking research and a DLR postdoc into technical leadership roles at Vay Technology and Tensordyne. His hands-on contributions include significant improvements to the widely used open-source deep_sort tracker—reworking model architectures with batch normalization, dropout and residual blocks, adding TensorFlow compatibility, supporting Python 2, and freezing models for efficient deployment. Nicolai blends research rigor with pragmatic engineering, routinely bridging camera/LiDAR sensor fusion, tracking, and inference optimization to deliver robust real-world perception pipelines.
9 years of coding experience
13 years of employment as a software developer
Dr. rer. nat., Dr. rer. nat. at Universität Koblenz-LandauUniversity of Koblenz and LandauArtificial Intelligence, Artificial Intelligence at University of Georgia - Franklin College of Arts and Sciences
German, English
Github Skills (11)
mask-rcnn10
computer-vision10
faster-rcnn10
machine-learning10
fasterrcnn10
tensorflow210
deep-learning10
tensorflow10
python10
model-optimization9
object-tracking9
Programming languages (2)
Github contributions (5)
nwojke/deep_sort
Feb 2017 - Jan 2019
Simple Online Realtime Tracking with a Deep Association Metric
Role in this project:
ML Engineer
ML EngineerContributions:29 commits, 19 PRs, 31 pushes in 1 year 11 months
Contributions summary:Nicolai primarily focused on modifying and enhancing the core deep learning components within the repository. Their contributions included significant updates to the model architecture, specifically involving batch normalization, dropout, and residual blocks. They also addressed TensorFlow version compatibility and implemented the freezing of the model for deployment, demonstrating a focus on optimizing the model for inference and real-world application. Furthermore, they adjusted detection and tracking components to ensure data integrity, and adapted the code for Python 2 compatibility.
realtimeassociationrealtime-trackingtrackingdeep-association-metric
nwojke/pymotutils
Aug 2017 - Aug 2018
Contributions:21 commits, 4 PRs, 15 pushes in 11 months
pythonpython-utilityobject-detectiontrackingmultiple-object-tracking
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.