Senior Software Engineer, DL Inference (TensorRT)

NVIDIA AI; Santa Clara (CA); On-site; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Senior Software Engineer for Deep Learning Inference to help build a state-of-the-art inference framework on NVIDIA GPUs, accelerating large language models. You will join the TensorRT Workflows team and tackle scalable, real-time inferencing challenges.

You will write in C++ and Python, optimize performance, and collaborate with GPU architects and ML researchers to push TensorRT forward.

Qualifications

• A Bachelor's, Master's, PhD or equivalent in Computer Science, Computer Engineering, Electrical Engineering or related field.
• 3+ years of software development experience.
• Strong experience with the latest C++ standards (C++11/14/17/20).
• Strong grasp of Machine Learning concepts.
• Experience and knowledge in Computer Architecture, Data Structures, Algorithms.
• Excellent communication skills and teamwork.

Responsibilities

• Craft and develop robust inferencing software scalable to multiple platforms for functionality and performance.
• Develop components of TensorRT, NVIDIA's SDK for high-performance deep learning inference.
• Follow academic developments in AI and update TensorRT accordingly.
• Use C++ and Python to build graph parsers, optimizers, and deployment tools.
• Collaborate with teams of deep learning experts, GPU architects and DevOps engineers.

Skills

C++ (latest standards)

Python

Machine Learning concepts

Computer Architecture

Communication

Education

BS/MS/PhD in CS/CE/EE or related

Tools

CUDA/OpenCL

TensorRT

PyTorch/TensorFlow/ONNX

Git

Job description

NVIDIA is seeking a Senior Software Engineer for Deep Learning Inference to help build a state-of-the-art inference framework on NVIDIA GPUs, accelerating large language models. You will join the TensorRT Workflows team and tackle scalable, real-time inferencing challenges.

You will write in C++ and Python, optimize performance, and collaborate with GPU architects and ML researchers to push TensorRT forward.