Roman Keller
Clinical Scientist Clinical Evaluation Lead
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolRoman Keller is a clinical scientist and clinical evaluation lead with 11 years of interdisciplinary experience at the intersection of digital health, biomedical research, and aerospace-inspired engineering. Currently leading clinical evaluation, regulatory submissions, and post-market surveillance for medical imaging devices in Zurich, he combines rigorous PhD-level research on digital health interventions with hands-on product support and customer training. His background includes large-scale behavioral data modeling to predict user receptivity, lab-based physiological research at ETH Zurich, and practical software development—contributing to prominent open-source drone projects like QGroundControl and PX4 where he improved UI and core flight-simulation fidelity. This blend of clinical rigor, regulatory know-how, and embedded systems experience gives him a rare ability to translate sensor-driven algorithms into compliant, user-centered medical products.
12 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Digital Health Interventions, Doctor of Philosophy - PhD, Digital Health Interventions at ETH ZürichMaster of Science - MSc, Health Sciences and Technology, Master of Science - MSc, Health Sciences and Technology at ETH Zurich
German, English, French
Github Skills (18)
simulation10
c-language10
gazebosim10
autopilot10
qt10
mavlink10
simulations10
drones10
user-interface10
sys10
system-integration10
sensor-fusion10
embedded10
vtk10
cprogramming-language10
Programming languages (11)
Github contributions (5)
RomanBapst/sitl_gazebo
Sep 2015 - Mar 2020
Role in this project:
Back-end Developer
Back-end DeveloperContributions:65 commits, 2 pushes, 5 branches in 4 years 6 months
Contributions summary:Roman primarily focused on modifying the `gazebo_mavlink_interface.cpp` file, indicating contributions to the core functionality of the `sitl_gazebo` repository. Their work included merging branches, converting to the NED coordinate system, adding noise to magnetic field calculations, and adapting the motor velocity calculation. These changes suggest a focus on improving simulation accuracy and integrating different components within the Gazebo environment.
PX4/PX4-Autopilot
Nov 2014 - Jan 2023
PX4 Autopilot Software
Role in this project:Back-end Developer
Back-end DeveloperContributions:410 reviews, 1024 commits, 719 PRs in 8 years 4 months
Contributions summary:Roman made several contributions to the PX4 Autopilot Software, which is designed for autonomous flight. Their work included adding sensor board rotation options to handle different sensor orientations, fixing style issues, and integrating code from the PX4 firmware repository. Additionally, they worked on modifying the attitude control for the tailsitter and updating the mission control behavior for a VTOL. These changes required an understanding of low-level sensor data integration, flight control algorithms, and the integration of different software modules.
px4pixhawkuavuasdronecode
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.