Join NVIDIA's innovative Local AI Inference team as a Senior System Software Engineer. Drive the development of robust system-level software and infrastructure for deploying, benchmarking, and qualifying high-quality AI applications and models. You will play a key role in shaping the future of AI infrastructure by building scalable systems, automating operations, and enabling engineers to diagnose complex issues. If you thrive on systems challenges and are passionate about AI, we want to hear from you.

NVIDIA has a rich history of innovation, from the GPU to leading the AI revolution. Our mission is to make the shift to autonomous AI seamless, efficient, and secure for users worldwide. This role offers a unique opportunity to contribute to cutting-edge AI technology.

Partner with benchmarking, inference, and AI application teams to define requirements and maintain infrastructure for AI workloads across various inference backends. Develop Git-based CI infrastructure for automated builds and testing across diverse hardware and software configurations. Build model management services for efficient download, versioning, and caching of checkpoints to ensure reproducible execution. Design databases, backend services, and data pipelines for storing and querying model metadata, benchmark results, and system telemetry. Create dashboards and reports to help engineers analyze inference configurations, identify performance bottlenecks, and investigate regressions.

Operate server infrastructure, including provisioning, scheduling, resource management, and failure recovery. Develop autonomous AI agents for infrastructure management, workload orchestration, monitoring, and diagnostics with robust access controls. Maintain Git repositories and companion websites, ensuring code, documentation, and evaluation results are up-to-date. Collaborate with inference developers to implement debugging capabilities, resolve system issues, and enhance infrastructure efficiency and scalability.

A B.Tech degree in Computer Science, Computer Engineering, Information Technology, Software Engineering, or a related field, or equivalent practical experience is required. You should possess at least 5 years of relevant software development experience, with strong programming proficiency in Python, C/C++, or C#. Experience in developing system software, backend services, or infrastructure supporting engineering development is essential.

A solid understanding of system APIs, multithreading, process and resource management, and systems debugging is necessary. Proficiency with Git-based CI, databases, SQL, and data modeling is expected. Excellent analytical and problem-solving skills, coupled with the ability to independently manage projects and priorities, are crucial. Strong written and verbal communication skills are required for effective collaboration across engineering teams.