NVIDIA Corporation in Santa Clara is seeking a Deep Learning Software Engineer for TensorRT performance to optimize the inference stack. You will analyze and improve performance across TensorRT, Torch-TensorRT, and related NVIDIA OSS projects, shaping low-latency DL workloads.
The role requires strong C++/Python skills and hands-on experience with DL frameworks, quantization and scheduling. Collaboration across AI and automotive domains is expected, with a focus on scalable inference across
#J-18808-LjbffrDL Inference Performance Engineer (TensorRT) in santa clara at Unknown Company
This position is listed as full time and onsite.