Senior AI Inference Architect — Kubernetes, GPUs, Equity

NVIDIA Corporation (old); Santa Clara (CA); On-site; USD 152,000 - 241,500; Full time

Job summary

A leading AI technology company is seeking a Solutions Architect to develop and enhance AI inference solutions using GPU technologies and Kubernetes. This role involves building inference pipelines, orchestrating disaggregated inference, and providing mentorship to teams. Applicants should have 5+ years of experience in Solutions Architecture, strong knowledge of distributed systems, and proficiency with NVIDIA tools. This position offers a competitive salary based on location and experience, with additional equity package opportunities.

Qualifications

• 5+ years in Solutions Architecture with a track record of deploying distributed systems.
• Experience with AI inference workloads and Kubernetes.
• Demonstrated success in tuning large language models.

Responsibilities

• Build inference pipelines with NVIDIA tools, improving efficiency.
• Collaborate with DevOps to orchestrate disaggregated inference.
• Provide mentorship and technical leadership to internal teams.

Skills

Kubernetes

NVIDIA Dynamo

TensorRT-LLM

Distributed systems

AI inference workloads

Education

BS in Computer Science/Engineering or equivalent experience

Tools

NVIDIA Triton Inference Server

NVIDIA GPU Operator

Job description

A leading AI technology company is seeking a Solutions Architect to develop and enhance AI inference solutions using GPU technologies and Kubernetes. This role involves building inference pipelines, orchestrating disaggregated inference, and providing mentorship to teams. Applicants should have 5+ years of experience in Solutions Architecture, strong knowledge of distributed systems, and proficiency with NVIDIA tools. This position offers a competitive salary based on location and experience, with additional equity package opportunities.