Deonna Owens

Bio

I am a Master’s student in Computer Science at Stanford University, where my research focuses on fairness, bias, and evaluation in large language models. I study how algorithmic evaluation frameworks can fail under social ambiguity and distributional shift, with an emphasis on LLM-as-Judge systems, multi-agent evaluation, and human-aligned benchmarking.

I have conducted research in both academic and industry settings, including work at Adobe Research and Amazon Robotics, and have collaborated with researchers in university labs on responsible and trustworthy AI.

I have been supported by competitive fellowships and scholarships and have held leadership roles in technical and community-focused organizations. Alongside my research, I have founded and led initiatives centered on mentorship, access to computing education, and professional development for underrepresented students.