System Software Engineer - Local AI

Role Overview

What You'll Be Doing

• Partner with software, research, architecture, and product teams to support the AI ecosystem on RTX and DGX PCs.
• Build and optimize local AI inference stacks for RTX, RTX Pro, and DGX GPUs across hardware architectures.
• Architect and develop inference runtimes and execution stacks for LLM, vision-language, TTS, ASR, and diffusion workloads.
• Work with Llama.cpp, vLLM, PyTorch, WinML, DXCGC, and TensorRT-RTX across inference workloads.
• Optimize models, data pipelines, and inference runtimes for current and next-generation GPU architectures.
• Apply quantization, pruning, sparsity, and distillation for efficient deployment on local and edge devices.
• Debug systems, optimize performance, analyze performance-accuracy trade-offs, and develop performance and accuracy sweep infrastructure.
• Establish engineering guidelines that accelerate bring-up and production readiness of models and inference backends.

What We Need To See

• At least 2 years of experience and a Bachelor's, Master's, or PhD in a related technical field, or equivalent experience.
• Excellent C++ programming and debugging skills with strong knowledge of data structures, algorithms, and machine learning.
• Proven experience with AI inference pipelines and applications using machine learning or deep learning frameworks.
• Interest in inference backend and runtime internals, including scheduling, memory management, KV-cache behavior, graph execution, quantization, and hardware-aware optimization.
• Strong analytical, problem-solving, multitasking, written communication, and oral communication abilities.

Ways To Stand Out From The Crowd

• Understanding of machine learning, deep neural networks, and generative AI techniques, with contributions to major open-source projects.
• Experience delivering end-to-end products with geographically distributed teams in multinational product companies.
• Proficiency in lower-level system or GPU programming, CUDA, and high-performance systems.
• Contributions to open-source inference runtimes, model tooling, or performance infrastructure.
• Hands-on experience with Llama.cpp, PyTorch, TensorRT, Vulkan, DirectX, or vLLM APIs and frameworks.

Employment

• The posting lists the time type as full time.