Senior Software Engineer, Deep Learning Inference - New HW Enablement

Details

Join NVIDIA's TensorRT team to enable support for emerging hardware capabilities in deep learning inference. You will integrate new hardware features into TensorRT's compiler and runtime, improve performance and functionality across the stack, and contribute high-quality C++ implementations aligned with modern C++ standards.

Responsibilities

• Orchestrate integration of new hardware functionalities into TensorRT's compiler and runtime.
• Work closely with teams and stakeholders across the hardware and software stack to understand and leverage new features to improve TensorRT's functionality and performance.
• Guide the design and implementation of robust, high-quality C++ code in alignment with Modern C++ standards.
• Contribute to continuous improvement of software practices and processes within the team.

Requirements

• Bachelors, Masters, PhD, or equivalent experience in Computer Engineering, Computer Science, Electrical Engineering, AI, or related fields.
• At least 8 years of relevant software development experience.
• Strong C++ skills, including knowledge of and application of best practices with C++11 and C++14.
• Familiarity with deep learning concepts and frameworks.
• Demonstrated initiative and track record of driving projects to completion.
• Excellent interpersonal skills and a collaborative, pragmatic approach to problem solving.

Ways to stand out

• Proficiency with Python and/or CUDA, ideally in a professional environment.
• Background with systems programming, embedded systems, and/or compiler development.
• Experience in software performance benchmarking, profiling, and optimizations.
• Experience with state-of-the-art deep learning models (such as Large Language Models) and frameworks for inference.
• Background with C++17 and other modern C++ standards.

Benefits and additional information

• Base salary ranges by level: Level 4: 184,000 USD - 287,500 USD; Level 5: 224,000 USD - 356,500 USD.
• Eligible for equity and benefits (see NVIDIA benefits page).
• Employment type: Full time.
• Office arrangement: Hybrid (#LI-Hybrid).
• Application deadline: Applications accepted at least until August 22, 2025.
• NVIDIA is an equal opportunity employer committed to diversity and inclusion.