Distinguished Engineer, End-to-End Scaling Performance Architecture

Job Title

Distinguished Engineer, End-to-End Scaling Performance Architecture

Role Summary

Lead long-term performance strategy for accelerated computing systems, spanning single-die to multi-GPU and multi-node platforms. Work with architecture, software, and application teams to turn workload behavior into measurable system-level priorities and guide multiple product generations.

Experience Level

Senior — 18+ years of relevant industry or academic experience, including setting architecture direction for complex, high-performance systems.

Responsibilities

Define and communicate an end-to-end strategy that aligns architecture and product decisions around application scaling and measurable performance outcomes.

• Define multi-generation strategy for scaling across DRAM, NVLink, chip-to-chip interconnects, compute, and supporting software.
• Translate AI, HPC, and accelerated computing workload behavior into architectural requirements, performance targets, and investment priorities.
• Analyze how bottlenecks change as workloads scale across dies, GPUs, nodes, model sizes, data sets, and communication patterns.
• Evaluate system-level trade-offs across bandwidth, latency, capacity, topology, coherence, power, area, cost, programmability, and resiliency.
• Establish common workload scenarios, scaling metrics, models, and decision frameworks for cross-team comparisons.
• Identify architectural discontinuities and emerging technology opportunities to influence product and technology decisions.
• Present clear, data-driven recommendations to senior technical and business leaders, including assumptions, risks, and expected impact.
• Mentor system performance architects and build technical communities across teams.

Requirements

Must-have technical skills and experience for success in this role.

• Deep expertise in system performance and scaling, including interactions among DRAM behavior, high-bandwidth fabrics (e.g., NVLink), and chip-to-chip communication.
• Strong application-level intuition: connect algorithms, parallelism, communication, locality, and data movement to architecture choices and outcomes.
• Experience with workload characterization, analytical or simulation-based performance modeling, bottleneck analysis, and architecture trade-off evaluation.
• Proven ability to create and advance multi-generation technical strategy through influence across silicon, systems, software, and application teams.
• Clear written and verbal communication skills; ability to explain complex system trade-offs to specialists and executives.
• Experience mentoring senior engineers into broader architecture leadership roles.

Nice-to-have:

• Track record of shaping product or technology roadmaps driven by application-level scaling needs.
• Examples of delivering measurable end-to-end improvements in performance, efficiency, or scaling.
• Experience with post-silicon validation, compilers/runtimes, or modeling tools for large-scale systems.

Education Requirements

MSEE, MSCE, PhD, or equivalent experience in Electrical Engineering, Computer Engineering, Computer Science, or a related field.

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.