At Touch, we are developing a unique personal health experience for our users through the use of AI health assistants. To achieve this, we have built an ecosystem of persistent models that incorporate expert systems, machine learning, and content distribution. Our main challenge has been to scale this stateful ecosystem in a robust way. In this talk, we will discuss the challenges we faced in developing and scaling our AI health assistants, including issues with model and state management, and maintaining the health and reliability of the interconnected components within the persistent ecosystem. We will describe our solution, which is built on top of Ray. Our talk will cover the overarching principles and design considerations that guided the development of our solution provide key takeaways for building and scaling similar products in other contexts.
As the co-founder of Touch Medical Intelligence, Josh Albert is dedicated to improving long-term health through the use of cutting-edge artificial intelligence technology. With a strong background in interdisciplinary research, including expertise in mathematics, physics, biology, and computation, Josh brings a unique blend of skills to his work in the field. During his PhD in astronomy, Josh applied his expertise in Bayesian methods to study a range of topics including galactic dynamics, the cosmic web, and Earth's ionosphere. He is also the author of the open-source Bayesian programming package, JAXNS, which has gained widespread recognition in the OpenScience world.
Come connect with the global community of thinkers and disruptors who are building and deploying the next generation of AI and ML applications.