Senior Infrastructure Software Engineer, TensorRT Edge-LLM

at Nvidia

USD 184,000-287,500 per year

SENIOR

✅ Hybrid

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI AWS @ 4 Azure @ 4 CI/CD Design Patterns @ 4 DevOps @ 4 Docker GCP @ 4 GPU Git @ 6 GitHub @ 4 GitHub Actions @ 4 Jenkins @ 4 Kubernetes LLM @ 3 Python @ 3 Robotics SGLang @ 3 Security Software Development @ 6 TensorRT @ 3 vLLM @ 3

Details

NVIDIA's TensorRT Infrastructure group is seeking a senior software engineer to enable the next generation of edge AI. The role involves defining the infrastructure and DevOps landscape for TensorRT Edge-LLM and developing scalable, modular infrastructure that streamlines development, builds, and testing across platforms including Drive AGX for autonomous vehicles and Jetson AGX for robotics and edge inference applications.

Responsibilities

Build and maintain the infrastructure required to deliver TensorRT Edge-LLM.
Maintain CI/CD pipelines to automate build, test, and deployment processes and improve build and test bottlenecks.
Configure, maintain, and extend industry-standard tools such as CMake, GitLab, GitHub Actions, Kubernetes, and Docker.
Develop throughout the software stack, from user experiences and interfaces to cluster layers.
Monitor and configure embedded and desktop CPU and GPU systems to ensure high CI/CD reliability.
Enable scanning and handling of security CVEs for infrastructure components.
Collaborate with external partners and work autonomously to design effective infrastructure solutions.

Requirements

Bachelor's degree or equivalent experience, or a higher degree, in Computer Science or Computer Engineering.
At least 7 years of proven experience.
Strong programming skills in Python or a similar language, with familiarity with modern C/C++ development.
Experience setting up, maintaining, and automating continuous integration systems such as Jenkins, GitHub Actions, or GitLab CI.
Experience administering, monitoring, and deploying systems and services on GitHub and cloud platforms such as AWS, GCP, or Azure.
Fluency in source control management systems such as Git or Perforce.
Experience with build systems such as CMake, Make, or Bazel.

Preferred Qualifications

Experience defining and owning DevOps strategy, including design patterns, reliability, and scaling, for a team or organization.
Deep understanding of test automation infrastructure, frameworks, and test analysis.
Familiarity with popular LLM frameworks and libraries such as TensorRT, TensorRT-LLM, vLLM, or SGLang.
Experience with mobile, embedded, or automotive platforms such as Ubuntu, JetPack, or QNX.
A track record of identifying useful technologies and incorporating them into software development workflows.

Benefits

The base salary range is USD 184,000 to USD 287,500 per year, depending on location, experience, and the pay of employees in similar positions. The role also includes eligibility for equity and benefits.

Applications will be accepted at least until August 10, 2026. NVIDIA is an equal opportunity employer committed to an inclusive work environment.