Senior Architect, Scaled AI Inference & GPU Acceleration

NVIDIA Corporation; Santa Clara (CA); On-site; USD 320,000 - 489,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA Corporation is seeking a senior architect to lead AI infrastructure and large-scale inference orchestration from Santa Clara. You will architect distributed pipelines, drive performance tuning from kernel to cloud, and influence open source projects to advance NVIDIA’s model serving on accelerated hardware.

The role requires deep GPU architecture knowledge, leadership, and collaborative impact across customers and teams. Equity, benefits, and a growth-focused environment are offered.

Qualifications

• 16+ years in technical roles with focus on AI infrastructure and large-scale inference orchestration.
• 7–10+ years of leadership experience.
• BS/MS or higher in systems / software engineering or equivalent.
• Deep technical expertise in GPU architecture, hardware acceleration, and low-level performance tuning (CUDA, kernels).

Responsibilities

• Architect distributed pipelines for high-throughput, low-latency inference systems.
• Lead hardware-software co-optimization and performance tuning at kernel/driver level.
• Guide open source projects (Dynamo, TensorRT-LLM, vLLM, SGLang, Ray) for NVIDIA hardware.
• Oversee lifecycle management for model serving across cloud and datacenter environments.
• Collaborate with customers, providers, and partners to set industry standards.

Skills

GPU architecture

Hardware acceleration

Low-level performance tuning

CUDA kernels

Cloud-native multi-tenant serving

Technical leadership

Communication & teamwork

Education

BS/MS or higher in systems/software engineering

Tools

Linux

Kubernetes

Ray

Dynamo

TensorRT-LLM

vLLM

SGLang

Linux kernel tooling

CUDA tooling

Job description

NVIDIA Corporation is seeking a senior architect to lead AI infrastructure and large-scale inference orchestration from Santa Clara. You will architect distributed pipelines, drive performance tuning from kernel to cloud, and influence open source projects to advance NVIDIA’s model serving on accelerated hardware.

The role requires deep GPU architecture knowledge, leadership, and collaborative impact across customers and teams. Equity, benefits, and a growth-focused environment are offered.