Lead Architect, AI Inference & Disaggregated Serving

NVIDIA; Santa Clara (CA); Vor Ort; USD 184.000 - 357.000; Vollzeit

Benefits dieser Stelle

Equity

Comprehensive benefits

Zusammenfassung

NVIDIA seeks an architect to reshape the AI inference landscape within its ISP team. You will help scale token generation on finite resources, lead high-stakes conversations with partners, and craft reference architectures that drive industry adoption.

Expect fast-learning, hands-on work from Kubernetes to kernel optimization, and mentorship across customers and teams. You’ll design and evangelize a leading tech stack, packaging best practices into reference architectures and guiding the

Qualifikationen

• 6+ years in solutions architecture or related roles driving deployments of distributed systems.
• 2+ years with AI workloads on Kubernetes.
• Experience with inference stacks such as Dynamo, Triton or TensorRT-LLM.
• Deep knowledge of disaggregated serving, KV caches, quantization and custom inference kernels.
• BS in CS/Engineering or equivalent experience.

Aufgaben

• Work with inference partners to demonstrate the value of our stack and gather product insights.
• Build and operate inference recipes to improve efficiency across GPU workers.
• Accelerate pipelines using TensorRT-LLM, vLLM and related backends for seamless integration.
• Evangelize DevOps best practices, Kubernetes clusters, compute fabrics and observability.
• Provide mentorship and leadership to customers and internal teams during deployment.

Kenntnisse

Solutions Architecture

Kubernetes

AI workloads

Distributed systems

Customer engagements

Ausbildung

BS in CS/Engineering or equivalent experience

Jobbeschreibung

NVIDIA seeks an architect to reshape the AI inference landscape within its ISP team. You will help scale token generation on finite resources, lead high-stakes conversations with partners, and craft reference architectures that drive industry adoption.

Expect fast-learning, hands-on work from Kubernetes to kernel optimization, and mentorship across customers and teams. You’ll design and evangelize a leading tech stack, packaging best practices into reference architectures and guiding the