Amna S.

I’m a PhD candidate working at the intersection of Human–Computer Interaction (HCI) and Generative AI, with a focus on LLM evaluation, data annotation, and research-driven AI systems. I’ve designed and deployed multiple LLM-based applications, conducted qualitative and mixed-method evaluations, and authored peer-reviewed research papers at A* venues (1 first-author, 2 co-author papers). I bring hands-on experience with: - LLM evaluation & benchmarking (task performance, failure modes, human-centered metrics) - Python-based experimentation, data analysis, and automation - Working with multiple LLM APIs as well as running models locally - Annotation design (annotation, guidelines, QA, inter-annotator agreement, qualitative coding) - Human-in-the-loop systems and user-centered AI evaluation I’m especially strong at bridging technical implementation with research rigor, translating vague goals into clear evaluation plans, annotation strategies, and actionable insights. I’m comfortable working independently, documenting decisions clearly, and iterating quickly based on feedback. If you’re looking for someone with hands-on experience in LLMs, data annotation, evaluation, and research, I’d be happy to help.