Andrey Smirnov
Machine Learning Engineer at Broad Institute of MIT and Harvard
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolAndrey Smirnov is a Machine Learning Engineer with 11 years of experience building production-grade pipelines and analytics for genomics and healthcare research at the Broad Institute in Cambridge, MA. He designs secure, cloud-native workflows that standardize and de-identify multimodal data, enabling scalable ML and predictive modeling across large cohorts. His engineering work spans from low-level variant-calling tool improvements (notably contributions to the flagship GATK repository) to cost-optimized copy-number analysis pipelines that cut cloud compute costs by roughly 60%. Andrey has delivered ML-based germline CNV detectors that improved accuracy across hundreds of thousands of UK Biobank samples, combining rigorous research with production reliability. He pairs a CS and Math background with hands-on software craftsmanship—refining Java-based genomics tools, WDL workflows, and integrated testing—to translate complex bioinformatics methods into reproducible, auditable systems. Colleagues rely on him for bridging research and operational engineering to make advanced genomics analyses both scalable and clinically useful.
11 years of coding experience
5 years of employment as a software developer
Bachelor of Science (B.S.), Computer Science and Mathematics, Bachelor of Science (B.S.), Computer Science and Mathematics at University of Massachusetts AmherstSaint Petersburg Lyceum 239
English, Russian
Github Skills (10)
bioinformatics10
javas10
genomics10
genome10
wdl10
gatk10
java10
genomes10
ng9
spark4
Programming languages (5)
Github contributions (5)
broadinstitute/gatk
Jul 2016 - Nov 2022
Official code repository for GATK versions 4 and up
Role in this project:
Backend Developer
Backend DeveloperContributions:19 reviews, 66 commits, 40 PRs in 6 years 5 months
Contributions summary:Andrey primarily contributed to the GATK codebase by modifying Java source code related to the Germline CNV Caller, and WDL scripts that are used in the GATK pipeline. These changes involved adjusting default values, fixing bugs in workflows, and updating filter names. The user's commits show work on the underlying tools as well as associated testing and workflow integration. They made improvements to the core functionality and workflow of the germline variant calling pipeline.
genomesciencednaspark-mlngs
broadinstitute/gatk-evaluation
Mar 2018 - Apr 2020
Contributions:8 PRs, 22 pushes, 7 branches in 2 years 2 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.