I am an ML researcher and software engineer with 8+ years of experience building production AI systems and researching trustworthy, auditable AI. Previously a Graduate Research Assistant at the Institute of Artificial Intelligence at the University of Georgia, where I completed an MS thesis on Interpretable AI for Image Classification under Dr. Jaewoo Lee.
Most recently, I was a Software Development Engineer at Amazon (Austin, TX), where I worked on payment and identity systems and prototyped LLM-based root cause analysis pipelines for incident remediation — work that directly motivated my current research.
I am now an ML Engineer on Omdena innovation challenges, building multi-agent AI systems and evaluation infrastructure. My active research focuses on a question that matters in production: how do you evaluate whether an LLM-generated remediation playbook is operationally safe — not just fluent — in environments where hallucinated recommendations cause real incidents?
My research interests sit at the intersection of LLM evaluation, agentic systems, and explainable AI — with a consistent focus on making AI decisions auditable, attributable, and trustworthy.
