jobs

System Software Engineer - Local AI

NVIDIA has continuously reinvented itself for over two decades. The invention of the GPU in 1999 fueled the growth of PC gaming, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU deep learning has

In inglese

Company

NVIDIA

Location

India, Pune

Status

Open

Posted

2026-09-09T00:00:00+00:00

NVIDIA's LocalAI team is hiring a Systems Software Engineer in Pune to build on-device AI software for RTX and DGX systems, focused on high-performance local inference, low latency and efficient memory use. Work covers inference runtimes such as Llama.cpp, vLLM, PyTorch, WinML, DXCGC and TensorRT-RTX, plus model optimization through quantization, pruning, sparsity and distillation. The posting asks for 4+ years of experience, strong C++ and debugging skills, and familiarity with ML/DL frameworks. CUDA and open-source contributions stand out.