NVIDIA is a world-class leader in AI workload optimization. They are seeking a Senior Software Engineer to automate and optimize performance analysis workflows for AI training and inference workloads, building scalable tools and workflows to support engineers. The role involves collaborating with various teams to align profiling capabilities with real-world AI workloads and developing automated solutions to detect performance bottlenecks.
Responsibilities:
- Design and build performance analysis tools and workflows for AI training and inference workloads
- Understand how AI performance engineers work and translate their needs into scalable, intuitive tooling
- Develop integrations between profiling infrastructure and AI frameworks and workflows
- Collaborate with performance engineers, hardware architects, and software teams to ensure profiling capabilities align with real-world AI workloads
- Identify performance bottlenecks in AI workloads and develop automated approaches to detect and diagnose them
Requirements:
- M.S., or PhD in Computer Science, Computer Engineering, or a related field (or equivalent experience). 6+ years of relevant work experience
- Deep knowledge of AI workloads, frameworks, and performance characteristics
- Experience building tools, workflows, or infrastructure used by other engineers
- Strong software development skills (Python, C++ preferred)
- Ability to translate user requirements into scalable tooling solutions
- Up to date with AI-enabled tooling for software development and performance analysis
- Strong interpersonal skills for understanding engineer difficulties and working across multi-functional teams
- Experience profiling or optimizing AI training or inference pipelines at scale
- Background building developer tools or platforms for ML engineers
- Contributions to open-source AI tooling or frameworks