Lead Engineer (Data Insights Team)
I focus mainly on strategic vision.
I counsel my team in data science methods and "big data" tools. We have leveraged variational Bayesian methods for intelligent posterior approximation as well as Spark and Kafka for distributed job execution. Under my direction, we created a working "K-prototypes" clustering algorithm capable of detecting anomalies via "distance" from cluster centers (representative of archetypal events).
As of late, I have been responsible for building out our CI/CD pipeline. I leverage Jenkins and Docker to ensure code that passes our expectations for function and quality are automatically delivered to the appropriate container registry for eventual deployment.