Speaker Details

Davide Menini
Hello! I'm Davide. Before delving into my work, let's start by mentioning that I have a deep passion for AI (who doesn't?), with a particular interest in the realm of Generative AI. If you share this interest, let's connect to share ideas and help each other stay updated on the latest advancements.I currently work as a Software Engineer in Swisscom's Conversational AI department, where I consider myself fortunate to transform my passion into tangible and beneficial solutions for others. My current responsibilities revolve around leveraging Large Language Models (LLMs) and associated frameworks to provide top-notch services to our customers. LLMs are powerful tools, but they truly shine when integrated into sophisticated and trustworthy applications capable of connecting them to reliable data sources and empowering them with reasoning capabilities. Before LLMs' era, I was developing Transformer-based AI services for tasks such as Intent Classification, Information Retrieval, and Machine Translation for our customer service chatbot.´╗┐Education-wise, I completed my BSc in Electronics Engineering at Politecnico di Milano, and later I received my MSc in Information Technology and Electrical Engineering from ETH Zurich, with a focus on Machine Learning and Computer Vision. Some time after my graduation I also published my Master Thesis work at ICRA 2022.
Hey ChatGPT, generate a comprehensive conference talk description that explores the world of Large Language Models (LLMs) within a rapidly changing and dynamic market. Emphasize the importance of agility and adaptability in this evolving landscape where unpredictability is the norm. Discuss the exploratory nature of the market, highlighting the quest to harness and monetize LLMs in new and existing products.
Compare various LLM models, such as OpenAI and llama, outlining their strengths and use cases. Dive into the concept of prompt engineering and its significance in optimizing LLM potential. Introduce relevant libraries for LLMs, including LangChain, AutoGen, and more, as valuable resources for developers.
Explore the concept of Retrieval Augmented Generation, focusing on its applications in Chatbots and autonomous agents interacting with knowledge bases.
Concluding by remarking on the significance of the talk in demystifying LLM complexities and affirming the relevance of this transformative technology.