AI researcher exploring methods to make large language models more understandable and applicable to real-world problems. Currently focused on neural computation, with previous work in natural language processing (NLP) on neuron-level interpretability, developing techniques to enhance the transparency and reliability of large language models.

Alongside research, I have a strong background in software development, game development, and DevOps. I love building websites, games, tools, experiments, and finding creative ways to bring ideas to life through code.