At Stellar ai, I annotated and evaluated datasets to support AI model training, reviewing responses for accuracy, relevance, and compliance with project guidelines. I also conducted quality checks to maintain data quality and support model performance.
For my AI Prompt Engineering & Evaluation Toolkit, I designed prompts for text summarization and multi-step logic, and built a Python workflow to batch-process AI API calls. I also developed WorkiFy, a full-stack task management application with authentication, role-based access, project management, and task tracking.
