Senior GPU AI Inference Systems Engineer (Dynamo-Triton)

NVIDIA Corporation; Santa Clara (CA); Presencial; USD 224 000 - 357 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity

Benefits

Resumo da oferta

NVIDIA Corporation is seeking a Senior System Software Engineer to advance the Dynamo-Triton Inference Server. You will build and optimize GPU-accelerated inference software, contribute to major feature work, and drive a unified, high-performance platform for LLM and non-LLM workloads.

You'll work in a fast-paced team focused on production-ready software, performance optimization, and collaboration with open-source communities. Equity and benefits are offered as part of the compensation package.

Qualificações

• MS or PhD in Computer Science or related field, or equivalent experience.
• 12+ years of professional deep learning software experience.
• Excellent Rust and C++ skills, with Python familiarity.
• Strong programming, debugging, performance analysis and test design.
• Experience with high-scale distributed and ML systems.
• Strong communication and teamwork in a fast-paced environment.

Responsabilidades

• Develop world-class GPU-accelerated AI inference serving software.
• Contribute to feature development and drive broad customer adoption.
• Converge Triton Inference Server and NVIDIA Dynamo stacks for a unified platform.
• Ensure feature parity for LLM and non-LLM workloads.
• Engage with open source DL software community.
• Balance performance, latency, and production deployment considerations.

Conhecimentos

Rust

C++

Python

Distributed systems

Performance analysis

Software design

Formação académica

MS or PhD in Computer Science

Ferramentas

GitHub

Linux

Open‑source contributions

TensorRT

Descrição da oferta de emprego

NVIDIA Corporation is seeking a Senior System Software Engineer to advance the Dynamo-Triton Inference Server. You will build and optimize GPU-accelerated inference software, contribute to major feature work, and drive a unified, high-performance platform for LLM and non-LLM workloads.

You'll work in a fast-paced team focused on production-ready software, performance optimization, and collaboration with open-source communities. Equity and benefits are offered as part of the compensation package.