Amir Sefidian is a senior data scientist and machine learning engineer based in Berlin with nearly two decades of computer science experience and nine years focused on ML in production. He currently improves search and reranking for Vinted’s 100M+ users, driving higher relevance and measurable lifts in transactions and GMV through automated retraining and monitoring systems. His background spans algorithmic trading—where he cut walk-forward optimization time by 83% and boosted portfolio RoR—and large-scale recommendation engines that materially increased CTR and conversion metrics. Amir also builds end-to-end ML services (from audio source separation to intent detection), authors educational content for 12K+ monthly learners via Sefidian Academy, and blends strong software engineering practices with research-grade modeling. Notably, he combines production-grade ML monitoring and profiling with hands-on optimization frameworks, making models both performant and robust in real-world systems.
9 years of coding experience
14 years of employment as a software developer
Master's degree, Computer Software Engineering, GPA: 4.0/4.0, Master's degree, Computer Software Engineering, GPA: 4.0/4.0 at Shahid Rajaee Teacher Training University
High School Diploma, Mathematics & Physics, GPA: 19.75/20, High School Diploma, Mathematics & Physics, GPA: 19.75/20 at Kosaran High School
Python package for fast and parallel transferring a bulk of files to S3 based on boto3!
Contributions:2 releases, 1 review, 27 commits in 3 months
multithreadingpythonparallelamazon-s3boto3
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.