Senior Product Manager: Adaptive Inference & Developer APIs

NVIDIA Corporation; Santa Clara (CA); On-site; USD 168,000 - 328,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA Corporation is seeking a Senior Product Manager to lead Switchyard, our adaptive inference runtime for models and runtimes. You will drive strategy, work with engineers and researchers, and translate research advances into scalable developer products.

You will collaborate with agent harness builders and partners to improve APIs, tooling, and adoption, delivering measurable outcomes in cost, latency, and quality at scale.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Engineering, AI/ML, or related field, or equivalent experience.
• 8+ years of product management or closely related experience building technical products for developers, infrastructure teams, or AI practitioners.
• Experience scaling developer or infrastructure products through a partnership motion and integrations.
• Technical proficiency in LLM inference, model routing, agent runtimes, and developer APIs.
• Able to reason clearly about quality/cost/latency tradeoffs.
• Ability to engage mature customers and partners independently, uncover production constraints, and guide GTM teams.
• Positive relationships with Engineering and Research teams.
• An evidence-driven product approach grounded in benchmarks, evals, and explicit success criteria.

Responsibilities

• Drive Switchyard’s product strategy and roadmap.
• Set priorities, quality bars, and clear product outcomes together with Engineering.
• Work directly with agent harness builders, inference gateways, model serving systems, and other partners to enable integrations.
• Define the developer experience and product interfaces for adaptive inference.
• Partner with Research to translate advances into usable products and features.
• Partner with Engineering to improve reliability, usability, documentation, SDK coverage, and production deployment paths.
• Build adoption motions with Product Marketing, Solution Architects, and GTM teams.
• Identify qualified workloads, guide partner pilots, and build repeatable deployment playbooks.
• Establish messaging for model routing and adaptive inference with Product Marketing.
• Define and inspect evidence for success and own the outcomes.
• Coordinate across adjacent teams to build compelling joint product outcomes.

Skills

Product leadership

Developer platforms

LLM inference

Model routing

Developer APIs

Stakeholder management

Cost/latency tradeoffs

Education

Bachelor's/Master's in CS or related field

Job description

NVIDIA Corporation is seeking a Senior Product Manager to lead Switchyard, our adaptive inference runtime for models and runtimes. You will drive strategy, work with engineers and researchers, and translate research advances into scalable developer products.

You will collaborate with agent harness builders and partners to improve APIs, tooling, and adoption, delivering measurable outcomes in cost, latency, and quality at scale.