Senior System Software Engineer - Local AI
Core
Architect and develop high-performance local AI inference software for RTX and DGX-class systems, focusing on low latency, optimized memory utilization, and deployment on resource-constrained platforms.
Role type
Senior IC systems software engineer (local AI inference)
Builds
High-performance local inference runtimes and execution stacks for LLM, vision-language, TTS, ASR, and diffusion-based AI workloads
Domain
AI computing, GPU systems, local/edge inference
Deliverable
production ML models
Required skills
C++ programming, AI inference pipeline architecture, model optimization (quantization, pruning, sparsity, distillation), system-level debugging, performance tuning, CUDA programming, low-level systems programming, data structures and algorithms, machine learning fundamentals
Preferred skills
AOT graph-compilation systems (TensorRT builder, MLIR), open-source inference runtime contributions, Vulkan/DirectX API development, multinational product delivery experience
Technologies
llama.cpp, vLLM, PyTorch, WinML, DXCGC, TensorRT-RTX, CUDA, Vulkan, DirectX
Responsibilities
Partner with software, research, and product leadership to align technical requirements; Build and optimize the local AI inference stack for diverse hardware architectures; Architect and develop modern inference runtimes; Perform end-to-end optimization of AI models and data pipelines; Lead system-level debugging and performance analysis; Mentor engineers and review architecture proposals
Seniority
Senior, hands-on IC with mentorship responsibilities
