
An hour to work through a technical choice, your direction in ML or GPU systems, or taking on greater engineering responsibility.
Bring the decision you’re facing and the options you’re considering. We’ll examine the trade-offs and assumptions, and identify practical next steps.
For a focused review of your GPU workload, performance measurements or inference architecture, choose GPU performance & inference review.
Please share a little context before the call and let me know early if you need to reschedule.