Product Manager - AI Inference & Model Serving
Core
Define product strategy and solution development for AI inference and model serving across on-premises, cloud, and edge environments to help customers deploy, scale, and operate production inference services.
Role type
Senior technical product manager (AI inference & model serving)
Builds
Production inference services, serverless inference, dedicated endpoints, autoscaling, routing, and observability tools for GPU infrastructure
Domain
Cloud-native infrastructure, distributed systems, GPU computing, AI/ML
Deliverable
production ML models
Required skills
Product strategy, technical product management, AI inference, model serving, serverless execution, autoscaling, routing, workload placement, observability, performance engineering, GPU scheduling, network optimization, storage optimization, system design trade-offs, go-to-market execution, pricing and packaging, reference architectures, customer engagement
Preferred skills
Experience with NeoClouds, sovereign clouds, enterprise platforms, disaggregated serving, multi-model serving
Technologies
vLLM, SGLang, TensorRT-LLM, Dynamo, Triton, Kubernetes
Responsibilities
Own product strategy, roadmap, and lifecycle for inference and model serving; Lead deep technical discovery with platform teams; Partner with engineering on system design trade-offs; Define positioning grounded in measurable outcomes; Drive go-to-market execution
Seniority
Senior, hands-on IC