Preethi Lahoti

Preethi Lahoti is a Senior Research Scientist at Google DeepMind, focusing on AI safety and alignment in Large Language Models. At DeepMind, they are a core contributor to Gemini and Bard AI safety modeling work. Preethi earned a PhD in Computer Science from the Max Planck Institute, with research centered on fairness in machine learning, and also holds an M.Sc. in Machine Learning from Aalto University. Their prior experience includes a software engineering role at Microsoft, where they developed large-scale systems and data solutions.