Summary
Sophie Guo is a machine learning engineer and founding team member building agent-driven lab automation and discovery in San Francisco, drawing on a decade of hands-on experience at the intersection of ML and biology. She holds a M.Eng. in EECS (AI) and dual BS degrees in Biological Engineering and EECS from MIT, and has applied representation learning, GNNs, and transformer architectures to single-cell and perturbational biology problems at MIT CSAIL and Cellarity. Her work spans industry and academia—from internships at Johnson & Johnson and Cellarity to translational research on knowledge graphs and novel wet-lab methods—and she focuses on interpretable models that reveal biological mechanisms. Sophie has led healthcare accelerators and taught ML for healthcare, combining technical depth with product-minded program leadership. She brings a rare blend of wet-lab intuition and scalable ML engineering, often leveraging knowledge-primed architectures to make models more biologically meaningful. Outside core research, she’s actively exploring single-cell foundation models and agentic lab automation as practical steps toward closing the loop between prediction and experiment.
10 years of coding experience
2 years of employment as a software developer
Master of Engineering - MEng, EECS with focus in AI, Master of Engineering - MEng, EECS with focus in AI at Massachusetts Institute of Technology
James Clemens High School