Senior Software Engineer, TensorRT Inference

Details

At NVIDIA, we're at the forefront of innovation, driving advancements in AI and machine learning to solve some of the world’s most challenging problems. We seek talented and motivated engineers to join our TensorRT team developing industry-leading deep learning inference software for NVIDIA AI accelerators.

Responsibilities

• Design, develop and optimize NVIDIA TensorRT to achieve tightly coordinated and responsive inference applications for datacenter, workstations, and PCs.
• Develop software in C++, Python, and CUDA to enable seamless and efficient deployment of state-of-the-art LLM and Generative AI models.
• Collaborate with deep learning experts and GPU architects to influence hardware and software strategy for inference.

Requirements

• BS, MS, PhD or equivalent experience in Computer Science, Computer Engineering or related field.
• 8+ years of software development experience on a large codebase or project.
• Strong proficiency in C++ and Python programming languages.
• Experience with development of deep learning frameworks, compilers, or system software.
• Foundational knowledge of machine learning techniques or GPU optimizations.
• Excellent problem-solving skills and ability to work effectively in a fast-paced, collaborative environment.
• Strong communication skills.

Ways to stand out

• Experience developing inference backends and compilers for GPUs.
• Knowledge of GPU programming and optimizations using CUDA or OpenCL.
• Experience working with LLM inference frameworks like TRT-LLM, vLLM, SGLang.
• Experience with deep learning frameworks like TensorRT, PyTorch, JAX.
• Knowledge of CUDA performance analysis, optimization techniques, and tools.

Benefits

• Base salary range: 184,000 USD - 356,500 USD.
• Eligibility for equity and benefits.

NVIDIA is committed to fostering a diverse work environment and is an equal opportunity employer. Applications accepted on an ongoing basis.