System Software Architect, AI Hardware and Software Performance

NVIDIA's Performance Lab (PerfLab) builds the automation platforms that evaluate the performance and quality of accelerated computing workloads efficiently and accurately, from single nodes to large training and inference clusters. Our platforms turn complex benchmark campaigns into reliable, scalable, and reproducible workflows, enabling engineering, product, and marketing teams to make data-driven decisions.

We are looking for a System Software Architect to set the technical direction for these platforms. You will build platform components and lead projects from problem discovery and technical design through production deployment and adoption. This hands-on role combines architecture, cross-team alignment, and direct system debugging. You will collaborate with NVIDIA teams around the world and help shape how NVIDIA measures, understands, and improves performance for large language models, agentic AI, and emerging HPC and AI workloads.

What You'll Be Doing:

• Define the technical direction and architecture for major areas of PerfLab's benchmark infrastructure, translating evolving business and engineering needs into clear roadmaps and scalable platform capabilities.
• Lead the implementation of reusable software, services, and workflows that automate benchmark definition, execution, result collection, validation, and reporting across local, cluster, and cloud-native environments.
• Establish engineering approaches that improve the reliability, scalability, observability, maintainability, and reproducibility of large benchmark campaigns.
• Stay hands-on with AI benchmarking, analysis, and benchmark design, and use that first-hand knowledge of how real workflows behave to ground platform investments and technical decisions.
• Lead delivery across team boundaries: align partner teams on direction, eliminate duplicated efforts, manage delivery risk, and keep stakeholders informed.
• Raise the engineering bar through architecture and code reviews, technical standards, and mentoring, while evaluating emerging technologies.
• Contribute to the strategy and development of internal and open-source projects, and grow their adoption.

What We Need to See:

• M.Sc. or Ph.D. in Computer Science, Electrical or Computer Engineering from a leading university (or equivalent experience).
• 10+ years of hands-on experience in developing system software, distributed systems, or AI systems.
• Strong Python and software engineering expertise, with a track record of building and operating production-quality tools, services, or automation frameworks.
• Proven technical leadership on sophisticated, multi-functional projects, including defining architecture, managing technical risk, resolving ambiguity, and driving solutions through delivery and adoption.
• Experience in quantitative analysis of AI hardware and systems, including hardware and system performance, architecture evaluation and power efficiency.
• Experience in operating distributed or cloud-native systems at scale, including performance profiling, capacity analysis, or resource scheduling.
• Excellent communication, influence, presentation, and cross-functional coordination skills, with experience aligning teams across countries and time zones to drive decisions.
• A record of mentoring engineers, raising engineering quality, and helping teams make better technical decisions.

Ways to Stand Out From the Crowd:

• Good technical understanding of modern compute hardware at one or more levels of the stack, including silicon, systems, networking, or clusters.
• Working knowledge of how AI workloads stress hardware, including memory bandwidth, memory capacity, interconnect communication, and real-world compute utilization.
• Practical experience building custom agent harnesses or strategies that improve workflows at team or organizational scale.
• Hands-on experience with AI training or inference frameworks such as vLLM, SGLang, TensorRT-LLM, PyTorch, or JAX.
• Demonstrated success turning loosely defined, cross-organizational problems into durable platforms or programs with measurable engineering impact.

We have some of the most forward-thinking and hardworking people in the world working for us. If you are creative, autonomous, and passionate about providing technical leadership while remaining hands-on in building systems that make complex AI performance work repeatable and scalable, we want to hear from you.