Summary
Christina L is a machine learning engineer and interpretability researcher with eight years of experience building scalable ML infrastructure and probing the inner workings of large language models. Currently a Member of Technical Staff (Resident) at Anthropic after a Research Fellowship focused on mapping persona subspaces and persona drift, she blends mechanistic interpretability with production-grade tooling. Her background includes engineering roles at DeepMind where she built Kubernetes- and JAX-based experimentation infrastructure, and internships at Google working on NLP data-quality heuristics. Christina holds a PhD in Computer Science from Oxford and a CS + Studio Art BA from Dartmouth, a combination that informs her interest in sociotechnical implications of AI and embodied, multimodal models. Notably, she has explored speculative and planetary-scale applications of AI—bridging research, systems, and philosophical inquiry into future-facing AI designs.
8 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Oxford
Bachelor's degree Computer Science Studio Art, Bachelor's degree Computer Science Studio Art at Dartmouth College
High School Diploma, High School Diploma at Cupertino High School