At Turing, I develop prompts for AI evaluation tasks and assess AI-generated responses for accuracy, relevance, reasoning quality, and instruction adherence. I use structured criteria to identify inconsistencies and produce clear analytical judgments.
At Tibexa Global, I supported AI-assisted data collection and processing, including cleaning, preparing, and validating data. I also contributed to web scraping and assisted with a demo web application, Supabase integration, and Vercel deployment.
My work has also included analyzing and visualizing business and research data at Podbee Media and Research İstanbul, and executing manual test cases at Dece Software. I built a Power BI dashboard for sales performance analysis and have worked on data annotation for computer vision.
