Hello! I am a final-year PhD student in Computer Science at the University of Washington, co-advised by Noah A. Smith and Yulia Tsvetkov. My research focuses on evaluating multimodal agents for real-world applications, emphasizing utility, safety, robustness, and societal impact. I also develop frameworks to assess fine-grained reasoning to enable model self-improvement, enabling safer and more effective deployment.

I have also worked extensively on multilingual language modeling, including high-quality data curation for pretraining and efficient tokenizer-free architectures. I also audited these models to improve safety and robustness across modalities and language varieties.

Before my PhD, I was a Research Engineer at Instadeep, working on AI solutions for enterprise clients. During my PhD, I interned at Google DeepMind , working on reasoning assessment and improvement in audio language models and at Apple MLR, working on enforcing alignment during multilingual LM pretraining.