I'm an AI scientist. I work on making AI systems more trustworthy.

My research looks at the reliability, interpretability, and security of large language models and agentic AI systems, mostly in the context of software engineering and organizational workflows. I'm interested in how these systems behave, where they fall short, and how to understand and improve what they're actually doing.

I'm currently a postdoctoral researcher at the Productivity and Security in Software Systems Lab at the University of Houston. Before that, I was a postdoc at Texas A&M University, and I got my PhD in Computer Science from the University of Houston. I also interned at Ericsson's Global AI Accelerator (US Hub), where I worked on AI training pipelines for telecom-focused NLP systems.

My work has been published at USENIX Security, ASPLOS, MSR, AIware, CAIN, and SeT LLM at ICLR, and supported by various institutions including NSF and SRI.

Explore my projects and publications. Click on the menu button on the top-left to learn more about my experiences.