Ahmed
Menshawy
VP, AI Engineering
Mastercard
Ahmed Menshawy is the Vice President of AI Engineering at Mastercard's Cyber and Intelligence division. In this role, he leads the AI Engineering team, driving the development and operationalization of AI products and addressing the broad range of challenges and technical debts surrounding ML pipelines. Ahmed also leads a team dedicated to creating a number of AI accelerators and capabilities, including Serving engines and Feature stores, aimed at enhancing various aspects of AI engineering. Ahmed is the co-author of "Deep Learning with TensorFlow" and the author of "Deep Learning by Example," focusing on advanced topics in deep learning. He is also collaborating on an upcoming O'Reilly book, "Graph Learning for the Enterprise," which aims to guide enterprises in efficiently training and deploying graph learning pipelines at scale.
16 April 2024 16:00 - 16:30
Optimizing the giants: navigating technical challenges and debt in LLMs deployment
Large Language Models (LLMs) have become an essential tool in advancing artificial intelligence and machine learning, enabling tremendous capabilities in natural language processing and understanding. However, the efficient deployment of LLMs in production environments reveals a complex landscape of technical challenges and debts. In this session, Ahmed will talk about the unique forms of technical challenges and debt associated with LLM deployment, including those related to memory management and parallelism, model compression, and attention optimization. These challenges emphasize the necessity of a custom approach to deploying LLMs, demanding customization and sophisticated engineering solutions not readily available in broad-use libraries.