Senior AI Inference Architect — Equity & Scalable GPU Solutions

2100 NVIDIA USA; Santa Clara (CA); On-site; USD 184,000 - 356,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA is seeking an experienced Solutions Architect to redefine AI inference infrastructure. You will lead high-stakes engagements, design scalable, disaggregated inference architectures, and mentor teams across customers and partners.

Expect deep collaboration with partners to push performance and reliability across GPU clusters and cloud environments. You will work with Dynamo, Triton Inference Server, and TensorRT-LLM to optimize models and pipelines, while guiding adoption of best-practices

Qualifications

• 6+ years in Solutions Architecture driving distributed deployments.
• 2+ years AI workloads on Kubernetes.
• Experience with Dynamo, Triton Inference Server, or TensorRT-LLM.
• Deep knowledge of disaggregated serving and multi-tier KV caches.
• BS in CS/Engineering or equivalent experience.

Responsibilities

• Work with inference partners to derive product insights for the industry.
• Build and operate inference recipes with tools like NVIDIA Dynamo.
• Accelerate inference pipelines with TensorRT-LLM and related backends.
• Advise on devops best practices for Kubernetes and observability.
• Provide mentorship and technical leadership to customers and teams.

Skills

Solutions Architecture

AI on Kubernetes

Kubernetes

DevOps practices

Mentorship

Education

BS in CS/Engineering

Tools

NVIDIA Dynamo

Triton Inference Server

SGLang

Job description

NVIDIA is seeking an experienced Solutions Architect to redefine AI inference infrastructure. You will lead high-stakes engagements, design scalable, disaggregated inference architectures, and mentor teams across customers and partners.

Expect deep collaboration with partners to push performance and reliability across GPU clusters and cloud environments. You will work with Dynamo, Triton Inference Server, and TensorRT-LLM to optimize models and pipelines, while guiding adoption of best-practices