System Software Engineer - Local AI

NVIDIA is seeking a Systems Software Engineer to build efficient on-device AI software for RTX and DGX-class systems, focusing on high-performance local inference, low latency, and efficient memory use.

The LocalAI team is working on delivering AI models locally, closer to the source of data, reducing latency, improving real-time processing, and addressing privacy concerns.

Responsibilities:

• Partner with NVIDIA's software, research, architecture, and product teams to align strategies and technical needs.
• Build and optimize local AI inference stack for RTX, RTX Pro, and DGX GPUs.
• Develop modern inference runtimes and execution stacks for frameworks like Llama.cpp, vLLM, PyTorch, WinML, DXCGC, and TensorRT-RTX.
• Perform end-to-end optimization of AI models, data pipelines, and inference runtimes.
• Conduct system-level debugging, performance optimization, and performance-accuracy trade-off analysis.

Requirements:

• 2+ years of experience with Bachelor's, Master's, or PhD in Computer Science, Software Engineering, Mathematics, or a related field.
• Excellent C++ programming and debugging skills.
• Proven experience working with AI inferencing pipelines and applications using ML/DL frameworks.
• Strong analytical and problem-solving abilities.
• Outstanding written and oral communication skills.

Benefits:

• Competitive salaries
• Generous benefits package
• Opportunities for growth and innovation