Summary
Brianna Chrisman is a Member of Technical Staff and research scientist blending eight years of machine learning and computational biology experience to build interpretable foundation models that accelerate scientific discovery. With a PhD from Stanford and hands-on roles at Anthropic and GRAIL, she has shipped clinically minded ML systems for early cancer detection and led projects that tied assay design to scalable, interpretable algorithms. Her recent independent work produced Local Loss Landscape Decomposition, a method for extracting interpretable circuits from deep networks, reflecting a rare focus on mechanistic understanding rather than black-box performance. Based in Palo Alto, she combines deep domain knowledge in genomics, microbiomics, and viral evolution with frontier LLM research to explore biological capabilities and risks of large models. Long term she aims to translate this cross-disciplinary expertise into biomolecule-based personalized medicines and population-scale pathogen detection or screening systems.
8 years of coding experience
8 years of employment as a software developer
Bachelor of Science (B.S.) Biomedical/Medical Engineering Applied Physics, Bachelor of Science (B.S.) Biomedical/Medical Engineering Applied Physics at Yale University
Doctor of Philosophy - PhD Bioengineering and Biomedical Engineering, Doctor of Philosophy - PhD Bioengineering and Biomedical Engineering at Stanford University
Spanish, English