Not specified (assumed to be flexible based on nvidia's culture of collaboration).
15+ years production software experience
Expertise in llm inference systems
Strong programming skills in rust, c++, python, cuda
NVIDIA is seeking a Principal Software Engineer specializing in AI Inference to enhance open-source LLM serving, focusing on performance optimization and collaboration within the infrastructure ecosystem. The role demands extensive experience in systems engineering, programming proficiency in languages like Rust and C++, and a deep understanding of inference systems
Job Summary
NVIDIA is the platform for every new AI-powered application.
This role involves contributing to upstream inference engines like vLLM and SGLang.
You will collaborate closely with internal model teams and product to ensure outstanding performance.
Matching Summary
Match Score: 85
NVIDIA is seeking a Principal Software Engineer specializing in AI Inference to enhance open-source LLM serving, focusing on performance optimization and collaboration within the infrastructure ecosystem. The role demands extensive experience in systems engineering, programming proficiency in languages like Rust and C++, and a deep understanding of inference systems.
Salary
Base: 272,000 USD - 431,250 USD; Bonus/Equity: Not specified; Benefits: Not specified
Skills & Requirements
Must-have
15+ years production software experience
Expertise in LLM inference systems
Strong programming skills in Rust, C++, Python, CUDA
Nice-to-have
Substantial open-source contributions
Experience optimizing full stack inference
Excellent communication skills
Key Requirements
BS/MS in Computer Science or related field
Demonstrated expertise in LLM inference/serving systems