AI Cloud Systems Engineer: LLM & Kubernetes

NVIDIA; Santa Clara (CA); On-site; USD 124,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Silicon Valley is seeking a System Software Engineer - AI and Cloud to join a team driving AI and cloud computing innovation. You will work on cloud-native AI workloads, RAG workflows, and advanced models, contributing to NVIDIA’s frameworks and deployment strategies.

Ideal candidates have 3+ years of Python/JavaScript experience, basic C++, and Kubernetes expertise, with a focus on scalable API design.

Qualifications

• Bachelor's or Master's in software engineering, CS, CE, EE, or related field
• 3+ years of experience
• Proficiency in Python and JavaScript for programming and debugging
• Basic familiarity with C++ in HPC environments
• Experience with cloud-native systems on Kubernetes using vLLM and Triton Inference Server
• Solid understanding of API design principles for scalable, production-ready inference systems

Responsibilities

• Evaluate cloud-native, full-stack applications using microservices to power AI use cases with NVIDIA frameworks and microservices
• Design and implement agentic workflows with RAG and modern AI models
• Evaluate user experiences and analyze AI solution performance, compiling findings into reports with improvement suggestions for executives
• Collaborate with product, marketing, hardware, software engineering, and QA to improve NVIDIA's offerings
• Develop developer-focused content, tutorials, and code samples to demonstrate NVIDIA tools and libraries
• Write technical whitepapers, product briefs, and run demos at industry conferences

Skills

Python

JavaScript

Data structures

Algorithms

APIs design principles

Cloud-native systems

Education

Bachelor's or Master's in Software Engineering, CS, CE, EE or related field

Tools

Kubernetes

vLLM

Triton Inference Server

Job description

NVIDIA in Silicon Valley is seeking a System Software Engineer - AI and Cloud to join a team driving AI and cloud computing innovation. You will work on cloud-native AI workloads, RAG workflows, and advanced models, contributing to NVIDIA’s frameworks and deployment strategies.

Ideal candidates have 3+ years of Python/JavaScript experience, basic C++, and Kubernetes expertise, with a focus on scalable API design.