Taedong Yun is a Senior Research Engineer with 11 years of experience at the intersection of machine learning, computational biology, and software engineering, currently working on autonomous agents at Google DeepMind. He holds a Ph.D. in Mathematics from MIT and has led research and engineering efforts across Google Brain, Google Health, and Genomics teams to translate ML advances into production-ready genomics and health AI systems. An active open-source contributor, he made notable back-end and CI/CD improvements to Google’s DeepVariant and Nucleus projects, including multi-sample variant support and gVCF generation for a widely used variant-calling pipeline. His background blends rigorous mathematical training with production engineering—optimizing major allele frequency calculations and hardening build/test infrastructure—so he navigates both theory and scalable systems. Based in Cambridge, MA, he also brings atypical operational discipline from prior military service and a track record of teaching advanced mathematics at MIT and KAIST.
11 years of coding experience
11 years of employment as a software developer
Gyeonggi Science High School
Ph.D. Mathematics, Ph.D. Mathematics at Massachusetts Institute of Technology
Harvard University
B.S. Mathematical Sciences, B.S. Mathematical Sciences at Korea Advanced Institute of Science and Technology
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 Developer & DevOps Engineer
Contributions:32 commits, 4 PRs, 1 push in 3 years 9 months
Contributions summary:Taedong made several contributions to the `google/deepvariant` repository, primarily focused on enhancing the core functionality and improving the build and testing infrastructure. Key contributions include adding support for specific alleles and multi-sample calls within the Nucleus library, which is integral to variant calling. They also addressed internal changes in the CI/CD pipeline, including fixing intermittent build failures and updating dependencies. Additionally, they added code to correctly generate gVCF records.
Python and C++ code for reading and writing genomics data.
Role in this project:
Back-end Developer
Contributions:11 commits, 6 comments, 2 issues in 3 years 4 months
Contributions summary:Taedong contributed to the `nucleus` repository by implementing and refining core functionalities related to genomic data processing. Their work involved adding support for various alleles, including symbolic ones, within the `is_snp` and `is_indel` utility functions. They also expanded the functionality of the `is_variant_call` function to support multi-sample calls. Furthermore, the user optimized code by speeding up major allele frequency calculations.
genomics-databioinformaticspythongenomics
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.