Senior Product Manager - AI Platform Inference
Core
Building tools, SDKs, and libraries to enable developers to deploy and optimize Generative AI models on NVIDIA GPUs.
Role type
Senior Product Manager (AI Platform Inference)
Builds
Inference deployment tools, SDKs, and optimization libraries for NVIDIA GPU platforms
Domain
Generative AI, High-Performance Computing, GPU Infrastructure
Deliverable
production ML models | product features
Required skills
Inference deployment and optimization software expertise, GenAI and machine learning concepts, performance optimization, software development and delivery, product strategy and roadmap creation, go-to-market planning
Preferred skills
Leading optimization products for Inference, Open Source & Github-first developer product experience, GPU architecture and HW/SW co-design knowledge, performance profiling
Technologies
vLLM, SGLang, FlashInfer, TensorRT-LLM, Triton, Dynamo, TorchAO
Responsibilities
Create products to help developers build better Inference deployments, Develop product strategy, roadmaps, and go-to-market plans, Collaborate with internal and external developers to build product-based roadmaps for model optimization software, Work with leadership to align with and drive company strategy
Seniority
Senior, hands-on IC
