Kishwar Shafin
Senior Research Scientist at Google
Los Angeles, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKishwar Shafin is a Senior Research Scientist at Google Health with nine years of experience applying machine learning to genomics, and currently the technical lead for flagship open-source projects including DeepVariant, DeepSomatic, DeepTrio, and DeepPolisher. He holds a Ph.D. in Biomolecular Engineering and Bioinformatics from UC Santa Cruz where his dissertation focused on nanopore sequencing and deep neural networks, and he has driven integration of pangenome methods into production variant callers. Kishwar’s contributions to the widely used DeepVariant pipeline include core example-generation and variant-calling improvements, ONT-specific model support, and haplotype-aware variant grouping—work that bridges research models and production-grade genomics tools. Based in Los Angeles, he blends deep academic training with hands-on ML engineering experience across industry labs (Google, NVIDIA) and has a track record of shipping open-source solutions that make high-accuracy genome inference accessible.
9 years of coding experience
9 years of employment as a software developer
Bachelor's Degree, Computer Science and Engineering, Bachelor's Degree, Computer Science and Engineering at Military Institute of Science and Technology (MIST)Doctor of Philosophy (Ph.D.), Biomolecular Engineering and Bioinformatics, Doctor of Philosophy (Ph.D.), Biomolecular Engineering and Bioinformatics at University of California, Santa Cruz - Jack Baskin School of Engineering
English, Bangla
Github Skills (8)
machine-learning10
tensorflow10
variants10
python10
deep-learning9
excel-dna8
bioinformatics8
ng8
Programming languages (6)
Github contributions (5)
google/deepvariant
Sep 2021 - Jun 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:
ML Engineer
ML EngineerContributions:3 releases, 3 commits, 3 PRs in 9 months
Contributions summary:Kishwar primarily contributed to the DeepVariant pipeline by modifying core modules related to example generation and variant calling. Their changes included internal modifications, fixing candidate filtering logic, and implementing features like haplotype labeling, particularly focusing on variant grouping by distance. Furthermore, the user worked on model-related aspects, such as fixing model initialization logic and integrating options for ONT (Oxford Nanopore Technologies) data, demonstrating an understanding of the DeepVariant's ML model pipeline and its customization for different sequencing technologies.
genomedeepvariantdnabioinformaticstensorflow
CGL-Deeplearning/FRIDAY
May 2018 - Oct 2018
Translation based variant caller
Contributions:403 commits, 4 PRs, 341 pushes in 5 months
translationcaller
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.