Senior PM, Inference Platform for Scaled AI

NVIDIA Corporation; Santa Clara (CA); On-site; USD 208,000 - 380,000; Full time

Job summary

NVIDIA Corporation in Santa Clara, CA is seeking a Product Manager for Inference Platform to define and drive products and platform capabilities enabling large-scale model serving across open source and proprietary models.

You will bridge AI research, infrastructure engineering, and real user needs, shaping architecture, APIs, capacity and cost management, and end-to-end product lifecycle for inference-related products. Equity and benefits are part of the package.

Qualifications

• 12+ years of experience delivering complex technical products.
• Bachelor's degree or higher, or equivalent experience.
• Strong written and verbal communication; ability to write clear product docs, specs, and strategies.
• Ability to operate in ambiguous, fast-paced environments and make progress without a full playbook.
• Analytical professional who can break down complex problems and drive decisions.
• Strong user empathy and ability to synthesize signals into a user needs picture.
• Deep familiarity with AI/ML systems and inference serving frameworks, and their tradeoffs.

Responsibilities

• Define product vision and strategy for inference platform capabilities (APIs, capacity management, cost management, performance, model serving infrastructure).
• Translate user needs and constraints into clear requirements and prioritized roadmaps.
• Partner with engineering, research, and user groups to drive execution from concept through launch.
• Own end-to-end product lifecycle for inference-related products and platform investments.
• Develop deep understanding of inference ecosystem, model formats, serving frameworks, and API formats.

Skills

AI/ML systems

Inference APIs design

Technical product management

Open source ecosystem

Education

Bachelor's degree or higher

Tools

TensorRT-LLM

vLLM

Triton Inference Server

Job description

NVIDIA Corporation in Santa Clara, CA is seeking a Product Manager for Inference Platform to define and drive products and platform capabilities enabling large-scale model serving across open source and proprietary models.

You will bridge AI research, infrastructure engineering, and real user needs, shaping architecture, APIs, capacity and cost management, and end-to-end product lifecycle for inference-related products. Equity and benefits are part of the package.