Lead Solutions Architect — AI Inference & Disaggregated Serving

NVIDIA Corporation; Santa Clara, Northern (CA, KY); Hybrid; USD 184,000 - 357,000; Full time

Benefits offered by this job

Competitive salaries

Comprehensive benefits package

Equal opportunity employer

Job summary

NVIDIA Corporation is seeking an experienced architect to transform AI inference in a high-demand, GPU-constrained landscape. You will lead multi-partner deployments, influence product directions, and deliver scalable disaggregated inference architectures.

You’ll collaborate with partners and internal teams to implement cutting-edge inference stacks, optimize kernels and runtimes, and guide complex deployments across large GPU clusters. This role anchors NVIDIA’s leadership in AI infrastructure.

Qualifications

• 6+ years in solutions architecture driving customer engagements to deploy distributed systems
• 2+ years with AI workloads on Kubernetes
• Hands-on full-stack agent design with sandboxing, memory and retrieval systems, evaluation and governance
• Experience with model optimization and serving tools (Dynamo, Triton, TensorRT-LLM)
• BS in CS/Engineering or equivalent experience

Responsibilities

• Work with inference partners to build and scale cutting-edge inference services
• Build and operate inference recipes with NVIDIA Dynamo and distribute tasks among GPU workers
• Accelerate inference pipelines with backends like TensorRT-LLM for seamless integration
• Mentor customers and internal teams through deployment of disaggregated inference systems

Skills

Solutions Architecture

Kubernetes

AI Workloads

Disaggregated Inference

Model optimization

Education

BS in CS/Engineering

Tools

NVIDIA Dynamo

Triton Inference Server

TensorRT-LLM

Job description

NVIDIA Corporation is seeking an experienced architect to transform AI inference in a high-demand, GPU-constrained landscape. You will lead multi-partner deployments, influence product directions, and deliver scalable disaggregated inference architectures.

You’ll collaborate with partners and internal teams to implement cutting-edge inference stacks, optimize kernels and runtimes, and guide complex deployments across large GPU clusters. This role anchors NVIDIA’s leadership in AI infrastructure.