Ananth Balashankar is a Senior Research Scientist at Google DeepMind in the GenAI Safety and Alignment team in New York. He works on improving the robustness and safety of classifiers and foundation models (Gemini LLMs) and applications (AI Overviews and AI Mode). His research spans the intersection of safe and responsible ML models with policy through methodologies including domain faithful optimization, data augmentation, adversarial training, and causal feature selection with publications at Science Advances, Nature sub journals, ACL, NeurIPS, ICML, etc. He has led work from basic research to product impact, with >10 launches that reach 1B+ users.

He received his Ph.D in Computer Science from NYU advised by Prof. Lakshminarayanan Subramanian and Dr. Alex Beutel (now at OpenAI). Before that, he worked as a Software Engineer at Google, and graduated from the Indian Institute of Technology, Kharagpur with B.Tech/M.Tech in Computer Science advised by Prof. Niloy Ganguly. He has served as the Area Editor for the ACM COMPASS, ACL; hosted a workshop at NeurIPS; and has received several awards including best paper awards at ICML, NAACL, best thesis and promising graduate awards at NYU.