I’m a software engineer and data scientist building open source tools for machine learning and insurance analytics. The projects I’ve worked on include sparklyr for interfacing with Apache Spark from R, MLflow for managing the ML lifecycle, mleap for packaging Spark ML models for deployment, and the R interface to TensorFlow and Keras for building deep learning models. I’m one of the authors of Mastering Spark with R. I’m also involved in the Kasa AI community for democratizing reproducible workflows and ML in the insurance industry.