DL Performance Software Engineer, LLM Inference

NVIDIA

full-time

Posted on: 9/25/2025

Origin: • 🇺🇸 United States • California

✨ AI Apply

💰 $120,000 - $235,750 per year

JuniorMid-Level

Distributed SystemsPythonPyTorch

About the role

Write safe, scalable, modular, and high-quality (C++/Python) code for our core backend software for LLM inference.
Perform benchmarking, profiling, and system-level programming for GPU applications.
Provide code reviews, design docs, and tutorials to facilitate collaboration among the team.
Conduct unit tests and performance tests for different stages of the inference pipeline.
Work and collaborate with teams involving resource orchestration, distributed systems, inference engine optimization, and writing high performance GPU kernels.
Architect and implement inference stacks to enable efficient, scalable, and accessible LLM inference.

Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent experience.
Strong coding skills in Python and C/C++.
2+ years of industry experience in software engineering or equivalent research experience.
Knowledgeable and passionate about machine learning and performance engineering.
Proven project experiences in building software where performance is one of its core offerings.
Solid fundamentals in machine learning, deep learning, operating systems, computer architecture and parallel programming.
Research experience in systems or machine learning.
Project experience in modern DL software such as PyTorch, CUDA, vLLM, SGLang, and TensorRT-LLM.
Experience with performance modelling, profiling, debug, and code optimization or architectural knowledge of CPU and GPU.
We strongly encourage including sample projects (e.g. Github) that demonstrate the qualifications above.