Profileimage by Kujtim Rahmani Computer vision engineer from Kumanovo

Kujtim Rahmani

available

Last update: 27.02.2024

Computer vision engineer

Company: Herr
Graduation: PHD Computer Science/ Machine Learning
Hourly-/Daily rates: show
Languages: German (Full Professional) | English (Full Professional) | Croatian (Limited professional) | Albanian (Native or Bilingual)

Attachments

Dr_270224.pdf

Skills


I (Kujtim Rahmani CV:https://bit.ly/3TencKd) am a Computer Vision/Machine Learning Engineer with more than 9 years of experience, encompassing more than ~ 6 years hands-on industrial involvement, coupled with 3.5 years of academic pursuits within the field of Computer Vision and Machine Learning.
I have lent my expertise as a consultant, primarily catering to prominent players in the German Automotive industry such as VW and BMW, and the German chemical industry, represented by Heraeus Group and Merck. I've also contributed as a Data Scientist researcher at Airbus. In these companies I have developed production, MVP and POC AI systems (Computer Vision, NLP and Intelligent Document processing) for optimizing the production and business processes as well as integrating them in  edge devives and/or cloud. 
 My journey has seen collaborations with several startups, including Zyncd, Rare Edition, Collx, Ramani, Pano.ai, Tolstoy.ai, HobbyBox and Smarauger. In these roles, I not only led the development of products (object detectors and trackers,  instance segmentation and image search), from their inception but also played a crucial role in resolving challenges by crafting highly accurate machine learning systems.
I hold a Ph.D. in Computer Science, specializing in Computer Vision and Machine Learning. My doctoral pursuits centered around the construction of hybrid methodologies, seamlessly blending traditional Machine Learning approaches with cutting-edge Deep Learning techniques, all directed towards the realm of urban scene understanding, 3D building reconstruction and facade segmentation
Beyond my primary focus, I hold an ardent passion for discrete mathematics and algorithms. My dedication is evident through my participation in over 100 competitions, wherein I've adeptly tackled diverse algorithmic and mathematical challenges. Notably, I take pride in achieving the title of "National Math Champion in North Macedonia" during my high school years.

Project history

07/2023 - Present
Senior Computer Vision Engineer
Pano.ai (Energy, water and environment, 50-250 employees)

Senior Data Scientist /Computer Vision (100% Remote Contract) at start-up Pano.ai
- Building computer vision algorithms for fire detection and tracking in the forest.
- Creating a tracking algorithm for tracking the fire during the night in the forest.
- Mathematical modelling of fire initiation and growth during the night.
Using: Python, OpenCV, Scikit-learn, GCP, GitHub

04/2023 - 07/2023
Senior Data Scientist
Smartauger (Industry and mechanical engineering, < 10 employees)

Senior Data Scientist/Computer Vision (Side Project) at Smartauger
- Building computer vision algorithms for object (pipes, optical fibre cables) detection in
electromagnetic wave generated image from Ground Penetrating Radar.
- Running experiments and building the algorithm on simulated and real data.
- Guiding the stake holders on how to acquire the data from the real scenarios.
Using: PyTorch, Python, OpenCV, Scikit-learn, AWS, GitHub

01/2023 - 06/2023
Senior Computer Vision Engineer
Ramani.io (Consumer goods and retail, 250-500 employees)

Senior Data Scientist /Computer Vision (100% Remote Contract) at start-up Ramani.io
- Building computer vision algorithms for object detection, counting and tracking in warehouses
- 3D reconstruction of the objects based on multiple images.
Using: PyTorch, Python, OpenCV, Heroku, Scikit-learn, AWS, Roboflow, Graph theory, GitHub

05/2021 - 03/2023
Senior Computer Vision Engineer
Rare Edition (Other, 10-50 employees)

Building computer vision algorithms for card defect evaluation. Quality Assurance for collectibles.

Using: Python, OpenCV, AWS, Matplotlib, TensorFlow, Keras

08/2022 - 01/2023
Senior Data Scientist
Heraeus Group (Pharmaceuticals and medical technology, >10.000 employees)

Senior Data Scientist /Computer Vision (100% Remote Contract) at Heraeus Group
- Building computer vision algorithms for object detection and tracking of defects of
manufactured parts in X-ray images.
- Optimize the detection and tracking to process more than ~17 images per second.
- Communicating with clients so that data and annotation achieve the best quality
Using: PyTorch, Python, OpenCV, Kalman Filters, Azure, Scikit-learn, Jupyter, GitHub, Pandas

06/2022 - 10/2022
Machine Learning Engineer
Tolstoy.ai (Energy, water and environment, < 10 employees)

Build an OCR automatic parsing of the data when they are uploaded on Google Drive
- Handled several templates
Used: Python, tesseract, pytesseract-OCR, Docker, OpenCV, GCP, Cloud Run, Scheduler

04/2020 - 07/2020
Data Scientist / NLP Engineer
(Telecommunications, 5000-10.000 employees)

Built an invoice data extraction algorithm for a private German digital post service.
Used: Python, OpenCV,Azure Cognitive Services, sci-kit learn, spaCy

07/2019 - 03/2020
Computer Vision Engineer
Volkswagen (Automotive and vehicle construction, >10.000 employees)

Built an object detection and tracking algorithm for counting objects in 3D Computed Tomography images of vehicle parts. Reduced the human (worker) time from ~120 minutes to 5 minutes.

Used: Python, OpenCV, Keras, TensorFlow, Azure Cognitive Services, sci-kit learn, Kalman Filters

04/2019 - 07/2019
Data Scientist Consultant
AIRBUS (Other, >10.000 employees)

System design for change detection in Airplane Cabin using Radio Frequency Signals.

10/2018 - 04/2019
Data Science Scientist
AIRBUS (Other, >10.000 employees)

Built a pore detection algorithm in 3D CT-Scans of airplane parts with 99.x% accuracy.
Used: Python, Tensorflow, Keras, sci-kit learn, and AWS.

06/2015 - 10/2018
Computer Vision Scientist
Bundeswehr University Munich, Institute of Applied Computer Science (Architecture and civil engineering, >10.000 employees)

Built a Semantic Scene Segmentation algorithm for façade images, which is state-of-the-art for small datasets.
- Created a dataset for detailed facade segmentation, including transoms and mullions of windows. First analyzed and considered these data for creating high-quality 3D building models.
- Built a complete pipeline for façade segmentation from data acquisition up to deployment.
Used: C++, OpenCV, Python, TensorFlow, and Matlab.

12/2014 - 05/2015
Machine learning engineer
zyncd.com (acquired by Capacity LLC) (Internet and Information Technology, < 10 employees)

Built a matching algorithm for user profiles with problem descriptions. Improved the accuracy
for more than 50%
Used: Python, SQL, sci-kit learn, word2vec and CherryPy

Certifications

Visual NLP for Data Scientists Certification
2023
Spark NLP for Data Scientists Certification
2023
Healthcare NLP for Data Scientists Certification
2023
From PhD to Innovator: DAAD
2022
Microsoft Certified: Azure Data Scientist Associate
2021

Local Availability

Open to travel worldwide
Profileimage by Kujtim Rahmani Computer vision engineer from Kumanovo Computer vision engineer
Register