Yavuz Kömeçoğlu
Founding Engineer at ThinkVoice AI
Istanbul, Istanbul, Turkey
Summary
👤
Senior🎓
Top SchoolYavuz Kömeçoğlu is a Founding Engineer and AI team lead with a decade of experience building production-grade machine learning systems, currently designing the core AI behind ThinkVoice’s call analytics platform. He combines hands-on research and productization—integrating call-center infrastructure, conversation analysis models, and actionable visualizations—to deliver scalable, user-validated solutions. Prior roles include ML R&D work on Turkish NLP, real-time news categorization and sentiment systems, and early full-stack development, giving him strong end-to-end delivery skills. An active contributor to the Hugging Face datasets hub, he has expanded Turkish-language resources for offensive language detection and sentiment analysis, bridging academic research and practical APIs. Based in Istanbul, he pairs a master’s in computer engineering with a mathematics background and a knack for turning research prototypes into robust commercial products.
10 years of coding experience
4 years of employment as a software developer
Yüksel-İlhan Alanyalı Anadolu Öğretmen LisesiMatematik, Matematik at Kocaeli UniversityYüksek Lisans (Master) Bilgisayar Mühendisliği, Yüksek Lisans (Master) Bilgisayar Mühendisliği at Okan University
Github Skills (7)
machine-learning10
nlp10
turkish10
python10
datasets10
data-engineering9
pandas9
Programming languages (8)
Github contributions (5)
huggingface/datasets
Dec 2020 - Jul 2021
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:6 reviews, 6 commits, 8 PRs in 7 months
Contributions summary:Yavuz primarily contributed to adding and updating datasets related to Turkish language tasks. They integrated new datasets, including offensive language, text categorization, and sentiment analysis datasets, by adding dataset configurations, data loading logic, and feature definitions. The user also updated existing datasets with improvements, reflecting a focus on expanding the available resources for Turkish NLP and machine learning model development within the Hugging Face datasets ecosystem. These contributions involve data processing, feature engineering, and integrating data within the Hugging Face datasets structure.
ml-modelstensorflownatural-language-processingmanipulationdata-science
yapay-ogrenme/casgem-eu-project-training-on-data-mining-2nd
Jul 2022 - Aug 2022
Contributions:57 commits, 49 pushes in 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.