You own outcomes. You don't stop where "infrastructure" ends. If the fix lives in backend code or the CVI stack, you dive in, and you don't wait for a ticket to do it
You're energized by unfamiliar problems. If the next thing that matters is standing up a training deployment you've never touched, you jump in and learn on the fly
You adapt as priorities evolve. In a space moving this fast, the most important thing to build can change as we learn. When it does, you adjust course without losing momentum
You care about this problem. Keeping large-scale, real-time systems fast and reliable is something you think about unprompted
Hands-on GPU inference experience. You've deployed and optimized inference workloads on GPUs and know what it takes to build reliable systems on top of GPU cloud providers
Kubernetes and EKS depth, including routing and scheduling. You're comfortable designing how work gets placed across a fleet, and writing the services that make it happen
Deep AWS experience. You're at home spinning up new services and turning them into simple, repeatable processes others can build on
A senior track record of ownership. You've set technical direction, made decisions others built on, and carried ambiguous work over the finish line. You explain complex ideas clearly, to engineers and non-engineers alike
Experience with GCP
Experience with video streaming infrastructure
Experience with training infrastructure or LLM serving
Experience with SOC2 or security compliance
If you don't check every box but this sounds like the work you want to be doing, apply anyway