AI Fellow — OpenAI/HandshakeAI
I developed and evaluated large language models (LLMs) to assess their performance on output tasks. My work focused on measuring aspects such as spatial reasoning, photorealism, and human anatomy using text-based outputs. This work was performed during my time as an AI Fellow at HandshakeAI/ OpenAI Move Fellowship. • Evaluated model-generated text for accuracy and realism • Conducted qualitative assessments of AI output correctness • Contributed to ongoing model improvement efforts • Reported findings to team leads for further analysis