Interview
summary
A platform constructs an activity graph from emails and meetings and wires it into Einstein to provide contextual services for other machine learning features. The work focuses on scalable data pipelines, graph architecture and the trade-offs made to keep queries fast and privacy-aware, and it reports that adding this context materially improves downstream models. Implementation uses Scala for engineering productivity and the team ships multiple products on the graph that are already in production.
AI-written summary · about
