About

Ahmed Metwally is a highly experienced Staff Software Engineer at Uber, with a focus on online fraud and abuse detection and prevention. With over 18 years of relevant experience and a PhD in large scale data analysis for detecting fraud in advertising networks, Ahmed has a wealth of expertise in this area. He is passionate about standardizing the landscape of how companies who handle users' data deal with their risks, user-trust and reputation, and is always open to collaborations across companies and with universities. At Uber, Ahmed is a Tech Lead of the Similarity-Clustering and the Graph-Clustering efforts, which cuts across Risk, Identity, Global Intelligence, and more. He is also a Tech Lead of the Account Integrity Team, ensuring that all Uber transactions are carried out by trusted and verified accounts. Previously, Ahmed worked as a Staff Software Engineer at LinkedIn, where he led the graph-clustering and the fuzzy-clustering efforts within the Artificial Intelligence organization, with its applications to abuse, anomaly detection, and content understanding. He also worked on account take over, fake accounts, and the underground fake-accounts market. Before that, Ahmed was a Senior Software Engineer at Google, where he worked with the AdSpam and the Anti-Abuse teams. There, he led and co-built a similarity-clustering framework that proposed the state of the art fuzzy-joins techniques and graph clustering and cluster merging techniques for detecting distributed attacks of click traffic and fake accounts. He also built several online and offline defenses against abusive click traffic, such as estimating the number of users behind all IP addresses, developing and tuning hotspot filters and distribution filters, and more. Ahmed's education includes an International General Certificate of Secondary Education from the University of Cambridge. His tech stack includes Senior Software Engineer, Software Engineer, ML, and infra. With his extensive experience and expertise, Ahmed is a valuable asset to any team working in fraud detection and prevention.