Mads Dyrmann
Founder at AI Lab ApS
Aarhus, Central Denmark Region, Denmark
Summary
👤
Senior🎓
Top SchoolMads Dyrmann is a founder and applied machine learning specialist with 12 years’ experience building computer vision and sensor systems for uncontrolled environments, particularly in agriculture and biodiversity monitoring. He has led development of camera-based pipelines and ML models that map weed distributions to optimize pesticide use and detect and count insect populations across urban, agricultural, and reserve settings. Academically grounded with a PhD in robotics and roles from postdoc to associate professor (Aarhus University) plus an honorary research association with Oxford, he blends rigorous research with product-focused engineering. Mads is hands-on in both hardware and software, contributing to open-source Python tooling (e.g., improving gputil) and routinely refactoring for maintainability and usability. He also has deep teaching experience in deep learning, robotics, and image processing, which informs his ability to translate complex methods into deployable systems.
12 years of coding experience
5 years of employment as a software developer
Det Kristne GymnasiumBS, Electronic Engineering, BS, Electronic Engineering at Engineering College of AarhusDoctor of Philosophy - PhD, Robotics Technology/Technician, Doctor of Philosophy - PhD, Robotics Technology/Technician at Syddansk UniversitetCand.Polyt, Teknisk IT, Cand.Polyt, Teknisk IT at Aarhus Universitet
Danish, English
Stackoverflow
11reputation
2kreached
3answers
1question
Github Skills (10)
refactoring10
python10
refactor10
numpy9
api-design8
performance-optimization8
pytorch6
shell6
jupyter-notebook6
exiftool6
Programming languages (8)
Github contributions (5)
anderskm/gputil
Aug 2017 - Aug 2017
A Python module for getting the GPU status from NVIDA GPUs using nvidia-smi programmically in Python
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 commits, 2 PRs in 1 day
Contributions summary:Mads primarily contributes to the `gputil` Python module, focusing on improving its functionality and maintainability. They refactored code to adhere to PEP-8 formatting, removing unnecessary dependencies like the "random" package. These improvements, along with simplified code, likely enhanced the readability and efficiency of the GPU status retrieval and management functions. The user's changes involved modifying core logic and enhancing the user experience by making the output more readable.
smipythonnvidianvidia-smigpu
au-mobile-robots/Exercises
Feb 2020 - Mar 2023
Contributions:73 pushes, 1 branch in 3 years 1 month
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.