Nish User

I am a detail-oriented and analytical AI Evaluator with two years of experience in assessing and improving AI models and systems. My proficiency lies in developing evaluation criteria, conducting comprehensive testing, and providing actionable feedback to enhance AI performance and reliability. I have a strong background in utilizing various evaluation tools and methodologies to ensure alignment with project goals and user needs.

In my recent role at Toloka, I conducted thorough evaluations of machine learning models, including natural language processing and computer vision systems. I developed and implemented tailored evaluation criteria and test cases, resulting in improved model performance. Collaborating with data scientists and engineers, I identified and resolved model issues, enhancing overall system reliability and user satisfaction. My experience as an AI Research Assistant at Universal Human Relevance System further honed my skills in data labeling and judgment tasks, contributing to the improvement of AI technologies.