Soroush Nasiriany
Optimus AI at Tesla
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolSoroush Nasiriany is a PhD-trained robotics and AI researcher with 11 years of engineering experience, currently working on Optimus AI at Tesla after completing a doctorate at UT Austin. He specializes in building foundation models for robotics by fusing internet-scale, synthetic, and real-world robot data to produce agents that generalize across diverse environments. His internships and research stints at NVIDIA, Google DeepMind, and Berkeley BAIR reflect a track record of shipping research-forward systems for embodied agents. An active contributor to open-source robot learning tooling (e.g., fixes to the widely used robomimic framework), he combines rigorous academic methods with practical experiment management and model refinement. Based in Palo Alto, he brings a rare mix of hands-on implementation chops and long-horizon research thinking focused on making robots reliably useful in the real world.
11 years of coding experience
5 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at University of California, BerkeleyDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at The University of Texas at Austin
French, Persian, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
pytorch10
machine-learning10
robotics10
python10
n9
rnn-model9
experiment9
mlops7
Programming languages (3)
Github contributions (5)
ARISE-Initiative/robomimic
Jan 2022 - Jul 2022
robomimic: A Modular Framework for Robot Learning from Demonstration
Role in this project:
ML Engineer
ML EngineerContributions:21 reviews, 40 commits, 27 PRs in 5 months
Contributions summary:Soroush contributed to the development of the robomimic framework by fixing a bug in the RNN_MIMO_MLP model, saving the configuration file for experiments, and removing unnecessary conditions within the robosuite environment interface. Additionally, the user made changes related to the VAE prior and updated the output directory path within the training utilities. These commits indicate a focus on model refinement and experiment management within the machine learning project.
modular-frameworkroboticslearning-from-demonstrationrobot-frameworkmachine-learning
robocasa/robocasa
May 2024 - Apr 2025
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Contributions:3 reviews, 2 PRs, 155 pushes in 10 months
humanoid-robotphysics-simulationrobot-learningrobotics
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.