Chandan Kumar

I’m a detail-oriented Information Technology graduate focused on AI quality and evaluation work. I combine strong attention to detail with hands-on experience in AI data annotation, LLM evaluation, and prompt assessment.

In my current role with OneForma (Centific), I evaluate AI-generated responses using detailed annotation guidelines for LLM training. I perform preference ranking, prompt evaluation, response assessment, and content validation while maintaining annotation quality, documentation accuracy, and process compliance.

I’ve also qualified multiple AI workflows, including Preference Ranking v5, GM Safety, Intelligent Polls, Action Items, 0 to 1 Composition, and Personalized Smart Replies. I take pride in active listening, professional customer communication, and clear documentation to support reliable AI outputs.

Earlier, as a Graduate Engineer Trainee (GET Intern) at NTPC Limited, I worked on anomaly detection model development. I handled data preprocessing, feature engineering, and exploratory data analysis, and I supported model evaluation and technical documentation—skills I now apply to AI operations and quality work.