High-Performance AI Inference Engineer (TensorRT)

NVIDIA Gruppe; Santa Clara (CA); On-site; USD 124,000 - 195,500; Full time

Job summary

NVIDIA Gruppe is looking for a passionate Software Engineer to join its TensorRT team in Santa Clara, California. This role involves designing and developing high-performance AI inference solutions while contributing to performance optimizations and collaborating with various teams.

The ideal candidate possesses a Master's or PhD in relevant fields and strong C++ skills. The position offers a competitive base salary ranging from 124,000 USD to 195,500 USD based on location and experience.

Qualifications

• Master's or PhD in Computer Engineering, Computer Science, Electrical Engineering, or AI.
• Strong foundational skills in C++, familiarity with modern C++ standards required.
• Interest in performance optimization and systems programming is a plus.

Responsibilities

• Contribute to the design and development of high-performance deep learning inference software.
• Collaborate with teams across the hardware and software stack.
• Support systematic reasoning about test plans and assist in documentation efforts.

Skills

C++ skills

Familiarity with C++11/14

Interpersonal skills

Performance optimization

Education

Master’s or PhD in relevant fields

Tools

C++ Standard Template Library (STL)

Python

CUDA

Job description

NVIDIA Gruppe is looking for a passionate Software Engineer to join its TensorRT team in Santa Clara, California. This role involves designing and developing high-performance AI inference solutions while contributing to performance optimizations and collaborating with various teams.

The ideal candidate possesses a Master's or PhD in relevant fields and strong C++ skills. The position offers a competitive base salary ranging from 124,000 USD to 195,500 USD based on location and experience.