AI Computing Software Development Engineer, TensorRT
Core
Building and optimizing GPU-accelerated deep learning inferencing software (TensorRT) for LLMs and generative AI across NVIDIA product lines.
Role type
Senior IC software development engineer (AI inferencing)
Builds
Production inferencing software and TensorRT updates
Domain
AI computing / Deep learning / GPU acceleration
Deliverable
production ML models
Required skills
C/C++ programming, performance analysis and tuning, deep learning frameworks (TensorFlow, Pytorch), software architecture design, scientific research publication
Preferred skills
Experience with LLMs and generative models, ability to work without supervision
Technologies
TensorRT, TensorFlow, PyTorch, C, C++
Responsibilities
Develop robust inferencing software scaled to multiple platforms, optimize performance, follow academic AI developments to update TensorRT, provide feedback on architecture and hardware design, collaborate with research and product teams, publish results in scientific conferences
Seniority
Mid-level, hands-on IC
