Georges Belanger Albarran

Georges is an Applied Research Scientist in the Adversarial Testing & Risk Evaluation squad at ServiceNow AI Research. He holds a Master’s degree in Computer Science from the Université de Montréal / MILA, completed under the supervision of Chris Pal. His thesis, Enhancing Factuality in Summarization, focused on factual summarization. In his previous roles — including at Microsoft Azure AI Platform — he worked on building entity extraction, extractive summarization, and key phrase extraction models served through APIs. He also has experience in client-facing roles, delivering consulting projects for the healthcare and entertainment industries. His current work at ServiceNow focuses on trust, safety, and security, including research on prompt injection attacks and red-teaming agentic workflows.