Senior Product Manager, Inference Platform
Core
Define and drive product strategy and capabilities for NVIDIA's Inference Platform to enable large-scale AI model serving for employees and partners.
Role type
Senior Product Manager, Inference Platform
Builds
Inference platform APIs, capacity management, cost management, and model serving infrastructure
Domain
AI/ML Infrastructure, Cloud Computing
Deliverable
product features
Required skills
Product strategy definition, Roadmap planning, User needs analysis, Technical product lifecycle management, Inference ecosystem knowledge, Ambiguity navigation, Stakeholder partnership
Preferred skills
Disaggregated prefill/decode, KV cache management, Speculative decoding, Continuous batching, Large scale systems, MLOps tooling, Capacity planning
Technologies
TensorRT-LLM, vLLM, Triton Inference Server
Responsibilities
Define product vision and strategy for inference platform capabilities, Translate user needs and infrastructure constraints into requirements, Partner with engineering and research teams, Drive end-to-end product lifecycle, Track developments in the inference landscape
Seniority
Senior, hands-on IC
