Dylan Nielson
Staff Scientist - Machine Learning Team at National Institute of Mental Health (NIMH)
Washington, District of Columbia, United States
Summary
👤
Senior🎓
Top SchoolDylan Nielson is a Staff Scientist on the Machine Learning Team at NIMH with 11 years of experience bridging neuroimaging, machine learning, and clinical research. He designs large-scale studies (including a funded 2,500-participant online project), consults across experimental design to analysis, and has shown methodological rigor by demonstrating when apparent predictive signals for depression are actually artifacts of analytic flexibility. A contributor to the widely used nipype neuroimaging workflows, he has extended interfaces and improved tooling that underpins reproducible analyses. His work combining mobile location/image data with neural measures has advanced basic questions about human memory, and his peer-reviewed review on reward processing in depression sits in the top 5% of tracked publications. Based in Washington, DC, he seeks roles where deep dataset immersion leads to tangible clinical impact.
11 years of coding experience
8 years of employment as a software developer
BS, Chemistry and Genetics, BS, Chemistry and Genetics at Clemson UniversitySouth Carolina Governor's School for Science & MathematicsPhD, Neuroscience, PhD, Neuroscience at The Ohio State University
English
Github Skills (7)
workflow-engine10
dataflow-programming10
dataflow10
python10
neuroimaging10
brain-imaging10
backend9
Programming languages (16)
Github contributions (5)
nipy/nipype
Jun 2017 - Nov 2017
Workflows and interfaces for neuroimaging packages
Role in this project:
Back-end Developer
Back-end DeveloperContributions:22 commits, 3 PRs, 11 comments in 5 months
Contributions summary:Dylan contributed significantly to the `nipype` repository, focusing on the implementation and enhancement of interfaces for neuroimaging packages, specifically within the `afni` module. They added new interfaces for tools like `3dqwarp`, `3dTnorm`, and `cat_matvec` which expanded the functionality of the library. Further contributions included refactoring and adding options to existing interfaces, and addressing documentation inconsistencies, demonstrating proficiency in maintaining and extending the codebase for neuroimaging workflows.
workflowneuroimagingpythondata-scienceworkflow-engine
Shotgunosine/fitlins
Sep 2019 - Jul 2022
Fit Linear Models to BIDS Datasets
Contributions:62 pushes, 6 branches in 2 years 10 months
linear-modelsfitlineardatasetsbids
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.