Staff Technical Program Manager, Inference
Core
Lead complex, cross-functional programs for CoreWeave's AI/ML Platform Services to deliver scalable, reliable inference workloads for serverless and dedicated use cases.
Role type
Staff Technical Program Manager (Inference Infrastructure)
Builds
Distributed inference services, GPU-accelerated cloud platforms, and customer onboarding workflows
Domain
AI/ML Infrastructure, Cloud Computing, Distributed Systems
Deliverable
production ML models
Required skills
Technical program management, distributed systems, inference infrastructure, GPU compute, cloud-native architectures, performance optimization, cross-functional leadership, launch readiness, operational excellence
Preferred skills
Inference-serving systems, model onboarding workflows, observability tooling, release validation, high-growth environment experience
Technologies
GPU, Cloud-native, Distributed systems
Responsibilities
Drive end-to-end program management for inference platform initiatives, lead cross-functional customer onboarding programs, drive launch readiness for new inference capabilities, partner with engineering to define roadmap outcomes for latency and throughput, coordinate multi-team execution for reliable inference services, build success metrics and dashboards for service reliability, establish repeatable processes for release validation and postmortem follow-through
Seniority
Staff, hands-on IC with strategic alignment
