Bago Amirbekian
Software Engineer - Machine Learning at Databricks
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolBago Amirbekian is a software engineer specializing in machine learning with 16 years of experience building production-grade data and ML tooling at Databricks and in academic research settings. He bridges research and engineering—moving from a PhD in bioengineering and neuroimaging pipelines at UC Berkeley/UCSF to delivering scalable ML and data-processing features in Apache Spark and Databricks. An active open-source contributor, he has improved core libraries like NumPy and Spark, enhanced deep-learning pipelines and image I/O, and automated complex release and cross-build workflows for GraphFrames. His work reflects a focus on robust, reproducible pipelines and performance (e.g., MLlib benchmarks and optimized searchsorted in NumPy), plus a knack for medical-imaging algorithms and visualization that informed earlier research tools. Based in San Francisco, he combines scientific rigor with practical DevOps and automation experience to ship maintainable systems at scale.
16 years of coding experience
6 years of employment as a software developer
University of California, Los AngelesPhD, Bioengineering, PhD, Bioengineering at University of California, San Francisco
Github Skills (43)
data-analysis10
algorithm10
algorithms10
apache-spark10
docker10
spark10
3d-graphics10
python10
image-processing10
testing10
dataframes10
big-data10
machine-learning10
sbt10
mathematical10
Programming languages (7)
Github contributions (5)
databricks/spark-deep-learning
Jun 2017 - May 2019
Deep Learning Pipelines for Apache Spark
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 17 commits, 21 PRs in 1 year 11 months
Contributions summary:Bago primarily contributed to the development and enhancement of image processing and deep learning pipelines within the Apache Spark environment. Their work included creating and refining image I/O functionalities, incorporating image resizing capabilities, and integrating models from Keras. The contributions also encompassed improvements to testing frameworks and the integration of pre-trained models, such as InceptionV3, for image feature extraction. The user also helped set up travis-ci for the repo.
data-sciencedeep-learningmachine-learningapachespark
dipy/dipy
Mar 2010 - Dec 2016
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
Role in this project:Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:472 commits, 15 PRs, 4 pushes in 6 years 10 months
Contributions summary:Bago made several code changes focusing on the development of a medical imaging library in Python. Their contributions included implementing functionality for Q-ball and ODF estimation, as well as working on different sampling functions on a sphere. The user also worked on various data structures like 4-D array to contain the model, and on various data input and output formats such as DSI.
signalpythonmicrostructurespatialtractography
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.