Summary
Sepehr Kazemian is a Machine Learning Engineer with nine years of experience applying LLM engineering, computer vision, and time-series forecasting to production problems across insurance, retail, and networking. He holds a Master's in Computer Science from the University of Alberta and has translated research on asymmetric costs and Markovian clustering into practical ML systems for risk modeling, pricing, and anomaly detection. At Munich Re he built LLM-driven summarization, Q&A and recommendation tools and deployed fraud and medical pricing models; at AltaML he created GAN-based imputation for missing time-series and explainable financial models. Now at Instacart, he continues to bridge cutting-edge algorithms with operational needs, focusing on scalable, explainable solutions that improve decision-making. Colleagues describe him as research-grounded yet product-minded, with a knack for turning academic ideas into robust, production-ready pipelines.
9 years of coding experience
6 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at University of Alberta
Amirkabir University of Technology
High School Diploma Mathematics and Physics, High School Diploma Mathematics and Physics at National Organization for Development of Exceptional Talents (Sampad)
English, farsi (persian), French