Streamlining NLP Model Creation and Inference

apply(conf) - May '22 - 10 minutes

At Primer we deliver applications with cutting-edge NLP models to surface actionable information from vast stores of unstructured text. The size of these models and our applications’ latency requirements create an operational challenge of deploying a model as a service. Furthermore, creation/customization of these models for our customers is difficult as model training requires the procurement, setup, and use of specialized hardware and software. Primer’s ML Platform team solved both of these problems, model training and serving, by creating Kubernetes operators. In this talk we will discuss why we chose the Kubernetes operator pattern to solve these problems and how the operators are designed.


Phillip North

Machine Learning Engineer

Primer.ai

Phillip is an engineer at Primer working on the ML Platform team. Prior to Primer he has worked both as an engineer and data scientist at various small start-ups.

Cary Goltermann

Machine Learning Engineer

Primer.ai

Cary is a software engineer at Primer where he works on the ML Platform team. Prior to joining Primer he worked for KPMG as a data scientist creating machine learning models and applications for tax professionals.