Gunjan Baid
Research Engineer at Google DeepMind
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolGunjan Baid is a research engineer with 11 years of experience at the intersection of machine learning and genomics, currently based in the San Francisco Bay Area and working at DeepMind. She has a strong track record at Google and Inductive Bio building production-ready ML systems, spanning genomics variant calling, multimodal models, and ultrasound interpretation. Her open-source contributions to high-profile projects like DeepVariant and Nucleus focus on making complex genomics pipelines reproducible and GPU-friendly—improving builds, Docker GPU support, and TensorFlow compatibility. Trained at UC Berkeley in CS and molecular & cell biology, she blends deep domain knowledge in biology with practical ML engineering. Colleagues describe her as someone who moves ideas from research prototypes to robust deployments, with an eye for automation and developer experience. An underappreciated strength is her hands-on experience resolving dependency and deployment bottlenecks that enable large-scale scientific ML workflows to run reliably.
11 years of coding experience
8 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at University of California, Berkeley
French, Hindi
Github Skills (23)
kubernetes10
docker10
jupyterhub10
python10
kubernetes-cluster10
machine-learning10
bash10
dockers10
cicd10
gcp10
script10
deep-learning10
tensorflow10
kubernetes-pods10
genomics10
Programming languages (6)
Github contributions (5)
google/nucleus
Jan 2019 - Jul 2021
Python and C++ code for reading and writing genomics data.
Role in this project:
ML Engineer
ML EngineerContributions:6 releases, 28 commits, 21 pushes in 2 years 6 months
Contributions summary:Gunjan primarily contributed to the "DNA Sequencing Error Correction" tutorial, focusing on deep learning applications within genomics. They implemented and updated code for the tutorial, including model architecture, TFRecord dataset generation, and TensorFlow 2.0 compatibility. The user also addressed typos, updated image paths, and ensured the code and documentation were aligned with Nucleus and TensorFlow best practices, which enhances the educational value and usability of the tutorial.
genomics-databioinformaticspythongenomics
google/deepvariant
Dec 2018 - Jul 2021
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:DevOps Engineer
DevOps EngineerContributions:1 release, 2 reviews, 100 commits in 2 years 8 months
Contributions summary:Gunjan's contributions primarily focus on improving the build and deployment processes for the DeepVariant project. They addressed the installation of dependencies, specifically managing TensorFlow and Intel-optimized TensorFlow versions. The user also updated scripts for the case studies and improved the Docker configuration for GPU support. These changes indicate a strong focus on automation and ensuring the project can be built and run efficiently.
genomedeepvariantdnabioinformaticstensorflow
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.