Pablo Velasco
Senior Scientific Solutions Engineer at Flywheel.io
Naples, Florida, United States
Summary
👤
Senior🎓
Top SchoolPablo Velasco is a Senior Scientific Solutions Engineer with over 20 years of MRI physics and neuroimaging experience who now blends hands-on engineering with operational leadership to deliver reproducible, automated imaging workflows. He led MRI operations and tool development at NYU’s Center for Brain Imaging—creating open-source projects like bidsphysio and contributing to heudiconv—and now applies that domain expertise at Flywheel.io to help labs scale data pipelines. His work spans image reconstruction, scanner QA, real-time data monitoring, and novel EPI artifact-reduction techniques, and he has contributed low-level fixes and optimizations to the prominent Gadgetron medical image reconstruction framework. Known for championing reproducibility via Dockerized pipelines and detailed provenance, he focuses on freeing researchers from tedious preprocessing so they can do more science. Based in Naples, Florida, he pairs a PhD in physics with practical software and systems skills that bridge academia and production deployments.
10 years of coding experience
17 years of employment as a software developer
Ph.D., Physics (Materials), Ph.D., Physics (Materials) at Universidad Autónoma de MadridB.Sc., Physics, B.Sc., Physics at Universidad Complutense de Madrid
Github Skills (7)
image-reconstruction10
c-language10
cprogramming-language10
complex-numbers10
linear-algebra9
fft8
fftw8
Programming languages (8)
Github contributions (5)
gadgetron/gadgetron
Oct 2015 - Dec 2016
Gadgetron - Medical Image Reconstruction Framework
Role in this project:
Back-end Developer
Back-end DeveloperContributions:46 commits, 32 PRs, 43 comments in 1 year 2 months
Contributions summary:Pablo primarily focused on improving the Gadgetron framework by adding and modifying core mathematical functions, particularly for handling complex data types. They added and optimized functions like `abs`, `addEpsilon`, `complex_to_real`, `dotc`, and `dotu` for `hoNDArray<complext>` data structures. The user also fixed bugs in reconstruction algorithms, specifically in iFFT and EPI reconstruction processes, demonstrating a solid understanding of image processing techniques. In addition, they fixed typos and removed unused variables and added comments to the code.
reconstructionimage-reconstructionmedical-imagedeep-learningcomputer-vision
cbinyu/heudiconv
Feb 2018 - Jan 2022
A flexible DICOM converter for organizing brain imaging data into structured directory layouts
Contributions:21 releases, 5 reviews, 124 commits in 3 years 11 months
brainflexiblelayoutsstructureddicom
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.