Martin Traud
Software Developer at IES Ltd.
United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolMartin Traud is a software developer with 10 years of experience who blends aerospace engineering expertise with practical software and ML engineering. He has delivered space-focused simulation and analysis tools—ranging from spacecraft attitude and debris/re-entry modeling to reliability and EMC measurement software—while transitioning into backend and machine-learning contributions for photorealistic training pipelines. At etamax space and DLR he combined project support and process improvements for flight experiments, and his recent work at IES Ltd. continues that mix of engineering rigor and software delivery. An active open-source contributor, he enhanced the BOP benchmark tooling and integrated TLESS dataset support into BlenderProc to enable accurate 6D pose data generation for training. Comfortable across scientific computing, simulation, and backend systems, he brings domain depth in aerospace coupled with hands-on coding that bridges research and production.
10 years of coding experience
3 years of employment as a software developer
B. Eng., Aerospace Engineering (Aerospace Electronics), B. Eng., Aerospace Engineering (Aerospace Electronics) at Baden-Wuerttemberg Cooperative State University (DHBW)M. Sc., Aerospace Engineering, M. Sc., Aerospace Engineering at Technische Universität BraunschweigUniversity of Oklahoma
Github Skills (12)
data-handling10
data-loading10
dataloader10
python10
load-data10
linear-algebra10
data-processing10
computer-graphics9
data-visualisation9
data-visualization9
data-visualizations9
image-processing8
Programming languages (5)
Github contributions (5)
thodan/bop_toolkit
Jul 2019 - Jul 2022
A Python toolkit of the BOP benchmark for 6D object pose estimation.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:51 reviews, 61 commits, 36 PRs in 3 years
Contributions summary:Martin's primary contribution focused on enhancing the BOP benchmark toolkit. This involved modifying the `calc_area_under_recall.py` and `eval_bop19.py` scripts to print final output scores and generate precision-recall plots. The changes involved additions to the existing code, including modifications to the visualization functions to generate plots. This work streamlined the evaluation process.
object-pose-estimationpythonpose-estimationbenchmarkestimation
DLR-RM/BlenderProc
Sep 2019 - Jan 2023
A procedural Blender pipeline for photorealistic training image generation
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:77 reviews, 726 commits, 49 PRs in 3 years 4 months
Contributions summary:Martin focused on integrating support for the BOP (Benchmark for 6D Object Pose Estimation) dataset by implementing the necessary functionality to load and process data from the TLESS dataset. This includes loading 3D models, parsing camera parameters, and applying transformations to correctly position objects in a scene, specifically within a procedural Blender pipeline used for generating photorealistic training images. The user demonstrated proficiency in modifying existing code, creating new classes, and adding functionality to extract parameters and transformations for object pose estimation.
structure-from-motionpythonblenderfeature-matching3d-engines
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.