Product Manager, Inference Platform
Core
Build a cloud platform for AI inference, training, and agent execution, enabling developers to ship AI products efficiently.
Role type
Senior Product Manager, Inference Platform
Builds
A coherent cloud platform for AI inference, training, and agent execution
Domain
AI Infrastructure / Cloud Computing
Deliverable
production ML models
Required skills
AI/ML product shipping, software engineering background, model serving architectures, GPU economics, performance benchmarking, customer workload analysis, release readiness
Preferred skills
PyTorch, vLLM, TensorRT-LLM, SGLang, NVIDIA Dynamo, open-source inference projects, ML systems research
Technologies
PyTorch, vLLM, TensorRT-LLM, SGLang, NVIDIA Dynamo
Responsibilities
Translate advances in batching, caching, quantization, and serving architectures into product features; define benchmarks for latency, throughput, quality, and cost; partner with engineering on release readiness and regression testing; help customers understand tradeoffs in hardware and model configurations.
Seniority
Senior, hands-on IC
