NVIDIA's TensorRT team is looking for a Software Engineer to contribute to high-performance AI inference solutions for specialized platforms and applications, aiming to shape the performance and functionality of their products and maintain NVIDIA's position as an innovator in AI technology.
Requirements
- Strong foundational C++ skills, including familiarity with C++11 and 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
- Experience with Python and/or CUDA through coursework, internships, or personal projects
- Exposure to systems programming, embedded systems, and/or compiler concepts
- Experience in software performance analysis, profiling, or optimization techniques
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 to improve TensorRT's functionality and performance
- Participate in the development of robust, high-quality C++ code in alignment with Modern C++ standards
- Support systematic reasoning about test plans from unit to integration level
- Assist in documenting the properties of functions, classes, and systems to improve robustness
- Contribute to performance optimization and benchmarking efforts
- Help develop new features and capabilities for TensorRT to serve specialized customer needs
Other
- Masters, or PhD in relevant fields (Computer Engineering, Computer Science, Electrical Engineering, AI) or equivalent experience
- Demonstrated ability to take initiative and see projects through to completion
- Excellent interpersonal skills and a collaborative, pragmatic approach to solving problems
- If you're creative, autonomous, and love a challenge, come join our team
- Applications for this job will be accepted at least until August 30, 2025.
