Software Engineer, TensorRT Specialized Platforms - New College Grad 2025

at Nvidia

USD 124,000-195,500 per year

JUNIOR

✅ On-site

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 C @ 2 C++ @ 2 CUDA @ 3 Deep Learning @ 2 Performance Analysis @ 3 Performance Optimization @ 3 Profiling @ 3 Python @ 3 TensorRT @ 3

Details

Join NVIDIA's TensorRT team to develop high-performance AI inference solutions for specialized platforms and applications. The role focuses on deep learning inference software, performance optimization, and systems programming using modern C++.

Responsibilities

Contribute to the design and development of high-performance deep learning inference software using modern C++.
Collaborate with teams across the hardware and software stack to understand and leverage new technologies that improve TensorRT functionality and performance.
Develop robust, high-quality C++ code aligned with modern C++ standards.
Support systematic reasoning about test plans, from unit testing through integration testing.
Document the properties of functions, classes, and systems to improve robustness.
Contribute to performance optimization and benchmarking efforts.
Help develop new TensorRT features and capabilities for specialized customer needs.

Requirements

Master's or PhD degree in a relevant field, such as Computer Engineering, Computer Science, Electrical Engineering, or Artificial Intelligence, or equivalent experience.
Strong foundational C++ skills, including familiarity with C++11, C++14, or newer standards.
Familiarity with the C++ Standard Template Library (STL).
Familiarity with modern deep learning models and inference frameworks.
Interest in performance optimization and systems programming.
Demonstrated ability to take initiative and see projects through to completion.
Excellent interpersonal skills and a collaborative, pragmatic approach to problem-solving.

Preferred Qualifications

Experience with Python and/or CUDA through coursework, internships, or personal projects.
Exposure to systems programming, embedded systems, and/or compiler concepts.
Experience with software performance analysis, profiling, or optimization techniques.
Knowledge of C++17 or later standards.
Understanding of computer architecture, memory management, or parallel computing concepts.

Compensation and Benefits

Base salary range: $124,000-$195,500 USD, determined by location, experience, and pay for employees in similar positions.
Eligible for equity and benefits.
Applications accepted at least until June 2, 2026.
This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.
NVIDIA is an equal opportunity employer committed to an inclusive work environment.