Agile Data Science: Achieving Salesforce-Scale Machine Learning in Production with Sarah Aerni
Every company needs artificial intelligence in production to stay competitive. This is hard technically and also from a process standpoint. Many engineering organizations struggle to provide their data scientists with the tools needed to effectively deploy models into production and continuously iterate. So how does Salesforce make data science an Agile partner to over 100,000 customers?
Sarah Aerni shares the nuts and bolts of the company’s platform and details the Agile process behind it. From open source autoML library TransmogrifAI and experimentation to deployment and monitoring, Sarah covers the tools that make it possible for data scientists to rapidly iterate and adopt a truly Agile methodology.
TransmogrifAI makes it easy for Salesforce’s data scientists to contribute new ways of solving challenging problems and evaluating them at scale using experimentation frameworks. The platform helps them ship the code to production to all customers simultaneously, automating the process of retraining thousands of models and shipping billions of predictions per day. And with modeling comes the need to detect issues and identify opportunities for improvements. Sarah explains how Salesforce uses alerting and monitoring to keep track of the individual models that its 100,000+ customers can build in a completely automated way and drive the company’s data science backlog. Along the way, Sarah discusses lessons learned about rapid iteration and ensuring data science innovation continues according to a truly Agile methodology.
Sarah Aerni is a director of data science at Salesforce Einstein, where she leads teams building AI-powered applications using autoML. Previously, she led teams in healthcare and life sciences at Pivotal building models for customers and cofounded a company offering expert services in informatics to both academia and industry. Sarah holds a PhD in biomedical informatics from Stanford University, where she performed research at the interface of biomedicine and machine learning.