A shared serving-spend view is splitting at the point where routed requests are counted.
Finance needs a stable forecast, and ML engineering needs cost detail that still reflects retries and routes.
Who you’d be doing this for
“Finance asked why our number moved overnight, and I had two answers open.”
Sergio Silva · ML Engineering Manager
Runs production Model Serving workloads and must defend their operating spend to Finance.
What is at stake
Two self-service views show different monthly serving-spend totals for the same routed requests. You must weigh a fast transformation change against preserving governed access and reliable reconciliation.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- forecast speed vs reconciled serving cost
- route-level detail vs shared definitions
- self-service access vs row-level security
- pipeline change velocity vs SOX evidence
Why Databricks
Model Serving cost visibility determines whether enterprise AI workloads can be justified and operated with confidence.
Written with these in mind
Not your kind of problem? 107 more at Databricks, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.