LLM Turkey is an academy that teaches AI evaluation. In our 12-week EvalOps Specialist program you learn, hands-on, how to measure the accuracy, safety and consistency of language models.
No coding background required. Graduates earn the EvalOps Specialist title.
Language models produce wrong facts, incomplete answers and risky content every day. Demand is growing fast for specialists who catch these errors, compare models and score quality. This program builds that expertise from scratch.
Anyone who wants to become a specialist in evaluating AI models. Students, recent graduates, career changers and professionals who use AI at work are all welcome.
Two hours a week: the first hour is theory, the second is example-heavy practice. Weeks 1–7 complete all 12 scenarios and 9 parameters; week 8 is dedicated to building eval sets.
Real evaluation + IRR (Inter-Rater Reliability).
Judex is our own evaluation platform that scores Turkish language models across 9 parameters. Throughout the program you test real models on Judex and complete your final assessment there.
Meet JudexEnroll right away by card, or at a discount via bank transfer. Write to us with any questions.