A computer science researcher specializing in LLM Interpretability and Cognitively-Inspired AI. My objective is to develop robust, explainable systems by investigating the integration of human inductive biases and symbolic reasoning structures into neural models. My foundational experience includes a thesis on LLM input-output interactions and research in concept-based interpretability. I am now expanding this focus toward neurosymbolic architectures, evidenced by projects in program generation. I seek to advance this research with the aim of developing models capable of more robust and human-aligned reasoning.