Gherman Uritskiy
Senior Staff Applied Scientist at Amazon
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolGherman Uritskiy is a Senior Staff Applied Scientist in Seattle with a decade of experience applying machine learning to bioinformatics, genomics, and multi-omic data. He has led cross-disciplinary R&D at Amazon—bridging genetics, protein engineering, and generative LLMs—and currently directs ML data strategy for stealth biomedical programs. Earlier work includes developing production-grade bioinformatics platforms (ProxiMeta, ProxiPhage) and a novel de-novo variant caller for clinical infectious disease sequencing. A Johns Hopkins PhD, he is a prolific author and the principal developer of the widely used metaWRAP metagenomics pipeline, contributing deep back-end and DevOps improvements. Known for translating complex sequencing data into scalable cloud workflows, he combines hands-on algorithm design with operational rigor across AWS-based deployments.
10 years of coding experience
7 years of employment as a software developer
Johns Hopkins UniversitySystems Biology and Computer Science, Systems Biology and Computer Science at University of CalgaryBachelor of Science, Biology, General, Magna cum laude, Bachelor of Science, Biology, General, Magna cum laude at The Catholic University of America
Github Skills (17)
python10
scripting10
script10
bioinformatics10
sh10
shell10
metagenomics10
bash9
samtools9
data-analysis8
kraken8
krakend8
heatmap7
seaborn5
dockers4
Programming languages (4)
Github contributions (5)
bxlab/metaWRAP
Jun 2017 - May 2022
MetaWRAP - a flexible pipeline for genome-resolved metagenomic data analysis
Role in this project:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:16 releases, 303 commits, 6 PRs in 5 years
Contributions summary:Gherman primarily contributed to the metaWRAP pipeline by fixing bugs related to contig naming and heatmap visualizations. They also made significant changes to the binning modules and scripts, enhancing functionality and incorporating new features. Moreover, the user modified the assembly and read QC modules, and added annotations, indicating a focus on improving the core functionality and usability of the bioinformatics pipeline. The user also made updates to the documentation and configuration files.
data-analysisgenomemetagenomicspipelineminhash
bxlab/timeline_paper
Mar 2018 - Sep 2019
Contributions:1 release, 54 commits, 46 pushes in 1 year 5 months
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.