Kourosh Meshgi
Tech Lead & Chief Scientist at SelfMinds AI
Virginia, United States
Summary
👤
Senior🎓
Top SchoolKourosh Meshgi is a tech lead and chief scientist with 12+ years of experience building agentic, multimodal AI systems that learn from observation and improve via self-supervision. He designs end-to-end pipelines—such as Video-RAG for cross-modal retrieval and Automation-from-Demonstration—that bridge perception, planning, and execution so agents can translate raw video into reliable, executable actions. His background spans academia and industry, including a PhD from Kyoto University, RIKEN research, and applied R&D in robotics and autonomous mapping for cars and drones. Kourosh’s work uniquely blends imitation learning, retrieval-augmented generation, and active/self-correcting architectures to model user behavior and enable continuous adaptation in dynamic real-world settings. Based in Virginia, he leverages deep multimodal research to deliver practical automation and personalized behavior modeling at scale.
13 years of coding experience
9 years of employment as a software developer
MSc, Artificial Intelligence, MSc, Artificial Intelligence at Amirkabir University of TechnologyPhD, Graduate School of Informatics, PhD, Graduate School of Informatics at Kyoto UniversityDiploma, Mathematics and Physics, Diploma, Mathematics and Physics at Sadr High School
Persian, Japanese, English
Stackoverflow
522reputation
109kreached
3answers
0questions
Github Skills (9)
algorithm6
jupyter-notebook6
matlab6
math6
environment-variables6
colors6
locale6
python6
image-processing6
Github contributions (5)
meshgi/RGBD_Particle_Filter_Tracker
Sep 2013 - Jan 2014
Contributions:23 commits in 4 months
meshgi/meshgi.github.io
May 2020 - May 2026
Contributions:15 pushes, 3 branches in 6 years 1 month
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.