Senior Software Engineer - Local AI

About the role

NVIDIA is seeking a Senior Systems Software Engineer to solve client-side AI challenges on Windows and Linux PCs with limited resources. This role focuses on advancing AI execution locally to reduce latency, improve real-time processing, and address privacy concerns by minimizing reliance on centralized servers.

Responsibilities

• Partner with NVIDIA software, research, architecture, and product teams to align strategies and technical needs for fostering the ecosystem of AI on RTX and DGX PCs.
• Collaborate closely with industry partners to advance AI across critical domains—including graphics, web browsers, and edge devices—by driving innovation in both open and closed source technologies with an emphasis on system-level support.
• Improve performance on current and next-generation GPU architectures by conducting in-depth analysis and end-to-end optimization of AI models, data processing pipelines, and inference runtime features.
• Identify, evaluate, and implement compute and memory optimization techniques—such as quantization, distillation, and pruning—for large AI models; fine-tune and compress models to fit edge devices.

Requirements

• Bachelor's, Master's, or PhD in Computer Science, Software Engineering, Mathematics, or a related field (or equivalent experience).
• Excellent C++ programming and debugging skills with a strong understanding of data structures and algorithms.
• 5+ years of experience with proficiency in AI inferencing pipelines and applications using ML/DL frameworks, including ONNX RT, PyTorch, TensorRT, llama.cpp, and vLLM.
• Strong analytical and problem-solving abilities, with the ability to multitask effectively in a dynamic environment.
• Outstanding written and oral communication skills enabling effective collaboration with management and engineering teams.

Skills

• Understanding of modern techniques in Machine Learning, Deep Neural Networks, and Generative AI, with relevant contributions to major open-source projects (a plus).
• Consistent track record of delivering end-to-end products with geographically distributed teams in multinational product companies.
• Proficiency in lower-level system/GPU programming, CUDA, and developing high-performance systems.
• Hands-on experience building applications using APIs like ONNX RT, DirectX, PyTorch, TensorRT, Vulkan, and llama.cpp.

Pay

Base salary range: $152,000–$241,500 USD (Level 3) or $184,000–$287,500 USD (Level 4), depending on location, experience, and position level. Eligible for equity and benefits.