Senior System Software Engineer - Local AI
Core
Architecting and delivering high-performance local AI inference software for RTX and DGX-class systems to enable low-latency, privacy-preserving AI on-device.
Role type
Senior System Software Engineer (Local AI)
Builds
Local AI inference stack, runtimes, and execution stacks for LLM, vision-language, TTS, ASR, and diffusion workloads.
Domain
AI Computing / GPU Systems
Deliverable
production ML models
Required skills
C++ programming, data structures, algorithms, machine learning, system-level debugging, performance tuning, model optimization (quantization, pruning, sparsity, distillation), hardware-aware optimization, CUDA programming, low-level systems programming, memory management, graph execution, KV-cache behavior, scheduling
Preferred skills
AOT graph-compilation systems (TensorRT builder, MLIR), open-source inference runtime contributions, Vulkan, DirectX, vLLM, Windows ML, DXCGC
Technologies
llama.cpp, vLLM, PyTorch, WinML, DXCGC, TensorRT-RTX, CUDA, Vulkan, DirectX
Responsibilities
Partner with software, research, architecture, and product leadership to align technical requirements; Build and optimize local AI inference stack for diverse hardware architectures; Architect and develop modern inference runtimes and execution stacks; Perform end-to-end optimization of AI models and data pipelines; Lead system-level debugging, performance tuning, and performance-accuracy trade-off analysis; Mentor other engineers and review architecture proposals
Seniority
Senior, hands-on IC