Daniel Cook
Software Engineer at Google
Downers Grove, Illinois, United States
Summary
🤩
Rockstar🎓
Top SchoolDaniel Cook is a software engineer with 12 years of experience at the intersection of genomics and machine learning, currently building production systems at Google after an AI Residency focused on health. He has deep bioinformatics roots from Northwestern and the Francis Crick Institute, where he led large-scale sequencing pipelines, GWAS portals, and reproducible analysis tooling. Daniel contributes to high-profile open-source projects like Google’s DeepVariant, adding debugging and back-end features that expose candidate alleles for model inspection — a hint at his pragmatic blend of ML model awareness and systems engineering. Comfortable across cloud-based pipelines, Python/R tooling, and large data workflows, he brings both research rigor and production-focused delivery to complex genomics software.
11 years of coding experience
6 years of employment as a software developer
Biology (Emphasis on Genomics), Biology (Emphasis on Genomics) at Northwestern UniversityB.S, Biology, B.S, Biology at University of Iowa
English
Stackoverflow
43reputation
800reached
2answers
3questions
Github Skills (13)
tensorflow10
python10
machine-learning9
bioinformatics9
deep-learning9
maps6
html6
css6
dendrogram6
gis6
ggplot6
ggmap6
google-app-engine6
Programming languages (22)
Github contributions (5)
google/deepvariant
Dec 2020 - Oct 2022
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
Role in this project:
Back-end & ML Engineer
Back-end & ML EngineerContributions:3 reviews, 43 commits, 12 PRs in 1 year 10 months
Contributions summary:Daniel implemented features to optionally output all candidate alleles considered by DeepVariant for debugging purposes. This involved modifying the `postprocess_variants.py` file to include a new flag and incorporate the logic to output all candidate alleles as ALT alleles with a low GL score. Further commits refined the behavior of this flag and added the functionality to output the alleles into an INFO field. These changes suggest involvement in both the back-end processing pipeline and debugging aspects related to the machine learning model.
genomedeepvariantdnabioinformaticstensorflow
AndersenLab/cegwas
Aug 2015 - Mar 2020
Contributions:326 commits, 12 PRs, 267 pushes in 4 years 6 months
pipelinebioinformaticsmappingsphenotypeelegans
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.