Summary
Umar Igan is a data scientist with 8 years of experience and 5+ years focused on building and deploying machine learning solutions across CV, NLP, regression and classification problems. Based in Istanbul, he has delivered end-to-end systems—from OCR and recommendation engines to rare-event accident prediction—combining robust feature engineering, ensembling and production pipelines on AWS/GCP. He’s experienced in Python, TensorFlow, PyTorch and scikit-learn, and has practical MLOps skills (ETL, DBT, Flask, SQL/NoSQL) for turning models into reliable products. Umar also works with generative AI (LLM, TTS, VLM) including fine-tuning and evaluation, and maintains popular LLM models on Hugging Face with 30k+ downloads. A Kaggle Notebook Expert, he brings a data-driven mindset and an aptitude for squeezing signal from imbalanced or noisy datasets to improve real-world business metrics.
8 years of coding experience
4 years of employment as a software developer
Certificate Program Data Science, Certificate Program Data Science at Özyeğin University
Master's degree Data Science, Master's degree Data Science at Koç University
Lisans Derecesi Mühendislik Fiziği/Uygulamalı Fizik, Lisans Derecesi Mühendislik Fiziği/Uygulamalı Fizik at Gaziantep Üniversitesi
Turkish, İngilizce