Aliasghar Khani
Machine Learning Researcher at Autodesk
Vancouver, British Columbia, Canada
Summary
👤
Senior🎓
Top SchoolAliasghar Khani is a Senior Machine Learning Researcher based in Vancouver with nine years of experience building and scaling generative and robust AI systems. He specializes in motion generation and large-scale 3D generative models, having trained diffusion and autoregressive architectures on datasets exceeding millions of 3D samples and models up to ~800M parameters. At Autodesk he bridges research and engineering—running distributed training and inference with Ray on AWS to deliver realistic, controllable 3D motion. His work also emphasizes model robustness and safety, with NeurIPS publication experience (MaskTune) and practical methods for mitigating spurious correlations and explaining vision models via LLMs. Aliasghar combines hands-on systems skills (cluster administration, multi-GPU pipelines) with publication-grade research, and he often explores the creative edge of AI by applying text-to-image and segmentation techniques to real-world datasets. Colleagues describe him as curious and collaborative, driven to push generative AI toward both expressive and reliable outcomes.
9 years of coding experience
4 years of employment as a software developer
Bachelor of Science - BS, Computer engineer, Bachelor of Science - BS, Computer engineer at Sharif University of TechnologyShahid madani high school(sampad)Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Simon Fraser University
Azerbaijani, Persian, English
Github Skills (11)
python5
pyglet5
scientific-visualization5
windowing4
opengl4
vision-api3
game-development3
cross-platform2
attention-mechanism2
multimedia2
vision-transformer1
Programming languages (3)
Github contributions (5)
HEffatpanah/Sport3FrontEnd
Dec 2018 - Sep 2020
Contributions:53 pushes in 1 year 10 months
aliasgharkhani/Masktune
Sep 2022 - Jan 2023
Contributions:17 commits, 12 pushes, 1 comment in 3 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.