Senior Product Manager - Adaptive Inference Platform

NVIDIA; Santa Clara (CA); On-site; USD 168,000 - 259,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA is seeking a Senior Product Manager to lead Switchyard, our adaptive inference runtime for models. You will drive product strategy, work with engineering and researchers, and shape the developer experience for flexible model routing and inference.

You will partner with researchers and GTM teams to translate advances into practical features, improve SDK coverage, and guide production deployments, ensuring scalable developer adoption across the ecosystem.

Qualifications

• BS/MS in CS/Engineering or related field, or equivalent experience.
• 8+ years of product management for developer/infrastructure products.
• Experience scaling developer products via partnerships and integrations.
• Proficiency in LLM inference, routing, and developer APIs.

Responsibilities

• Define Switchyard product strategy and roadmap with engineering.
• Collaborate with agent harness builders, inference gateways, and model serving systems.
• Define developer experience and product interfaces for adaptive inference.
• Translate research into usable features with cost/quality tradeoffs.
• Improve reliability, usability, and SDK coverage for production deployments.
• Lead go-to-market coordination with marketing and partners.
• Develop messaging for model routing and adaptive inference.
• Own success metrics and outcomes across teams.
• Coordinate across adjacent teams for joint product outcomes.

Skills

LLM inference

model routing

developer APIs

stakeholder management

Education

CS/Engineering degree

Job description

NVIDIA is seeking a Senior Product Manager to lead Switchyard, our adaptive inference runtime for models. You will drive product strategy, work with engineering and researchers, and shape the developer experience for flexible model routing and inference.

You will partner with researchers and GTM teams to translate advances into practical features, improve SDK coverage, and guide production deployments, ensuring scalable developer adoption across the ecosystem.