Hello! ◡̈ I am a Computer Science graduate student at Texas A&M University–Corpus Christi, beginning my master's in Spring 2026. I graduated with a BS in Fall 2025, with minors in Mathematics and Criminal Justice.
I seek to pursue a Ph.D. in Computer Science focused on AI safety and alignment, with a career in academia, supported by three NSF REUs, research assistantships, and teaching experience.
My research centers on the safety and trustworthiness of agentic and multi-agent AI systems, particularly alignment failures, unsafe behavior in LLM agents, and LLM security. I am currently exploring directions in deceptive alignment, goal misgeneralization, and unsafe behaviors in the perception-action interface of computer-use agents. (See "Research" section!)
Beyond research, I taught College Algebra recitations, completed NSF mechatronics training at Michigan Tech, served as a CAHSI advocate, and led statewide student volunteer efforts.
Starting as a research fellow at PRISM (Peer-Vetted Research Initiative for Safety Methodologies) on LLM Decision Update Consistency (DUC) under epistemic conflict.
Starting the MIT AI Alignment (MAIA) AI Safety Fundamentals Fellowship (AISF) to deepen expertise in alignment theory and interpretability!