Siavash Khallaghi
Machine Learning Engineer at Meta
Vancouver, British Columbia, United States
Summary
👤
Senior🎓
Top SchoolSiavash Khallaghi is a machine learning engineer with 14 years of experience turning research-grade computer vision and medical-imaging algorithms into production systems, currently at Meta after leading applied ML teams at Prenuvo. He holds a PhD in Electrical and Computer Engineering and has deep expertise in ultrasound and image registration, having developed clinical-grade acquisition frameworks and published IEEE work during his academic career. Siavash blends low-level C++/Qt/VTK engineering with modern ML tooling—shipping models to production across startups and enterprises—and has contributed open-source implementations like a numpy-based Coherent Point Drift registration library. Known for bridging research and product, he often refactors legacy codebases for Python 3 compatibility and pragmatic deployment, and prefers tackling the “mysterious and important” problems others avoid.
14 years of coding experience
17 years of employment as a software developer
Amirkabir University of TechnologyPhD, Electrical and Computer Engineering, PhD, Electrical and Computer Engineering at The University of British ColumbiaMSc, Electrical and Computer Engineering, MSc, Electrical and Computer Engineering at Queen's University
German, English
Stackoverflow
436reputation
25kreached
24answers
10questions
Github Skills (13)
algorithm10
algorithms10
python10
implement10
numpy10
documentation8
lua6
itk6
fedora6
vtk6
machine-learning6
amazon-ec26
amazon-web-services6
Programming languages (9)
Github contributions (5)
siavashk/pycpd
Oct 2016 - Jun 2022
Role in this project:
Backend Developer
Backend DeveloperContributions:1 release, 49 commits, 13 PRs in 5 years 9 months
Contributions summary:Siavash primarily focused on implementing and refining the Coherent Point Drift (CPD) algorithm. They added features, like a skeleton for a new JRMPC rigid registration method. Further contributions included updating the README file to reflect code changes and the project's build status and correcting Python 3 compatibility issues. They also addressed some bugs, improved documentation and refactored parts of the codebase, most notably by modifying existing code.
coherentpythonsplinesnumpyfenics
siavashk/imagenet-autoencoder
Feb 2016 - Oct 2019
Contributions:9 commits, 7 pushes, 1 branch in 3 years 8 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.