Senior Power Architect, Power and Performance Analysis Tools

Job Title

Senior Power Architect, Power and Performance Analysis Tools

Role Summary

Own and advance a power estimation and analysis platform used to guide architecture and product decisions. The role combines software development, system and SoC architecture, performance modeling, and silicon analysis to produce actionable power-performance insights for architects and engineering teams.

Experience Level

Senior level. The posting requests approximately 6 years of relevant work experience.

Responsibilities

Deliver and maintain a production-grade toolset and methods for power and performance analysis across products and workloads.

• Define architecture, roadmap, development, and validation for power estimation and analysis tools.
• Implement scalable software to estimate and analyze power and performance across workloads and configurations.
• Build models that map architectural parameters, workload behavior, utilization, and telemetry to power-performance metrics.
• Support architectural trade-off analysis (performance, power, energy efficiency, thermals, performance-per-watt).
• Develop workload models and representative usage scenarios for early exploration and product analysis.
• Integrate silicon telemetry, performance counters, power measurements, traces, and simulation data into a unified framework.
• Correlate pre-silicon estimates with post-silicon measurements and improve prediction accuracy.
• Create automation, visualization, and reporting to make analysis accessible to architects and engineering teams.
• Partner with architecture, power/thermal, firmware, validation, and silicon teams to define requirements and drive decisions.
• Act as technical owner and subject-matter expert for the tool, support users, and grow contributors.

Requirements

Must-have technical skills, system knowledge, and software engineering practices required to deliver and operate power/performance analysis tools.

• Strong software development skills in Python, C++, or similar; experience building production engineering tools and platforms.
• Understanding of computer/SoC architecture: processors, memory systems, interconnects, accelerators, and power-management concepts.
• Experience with power and performance estimation, performance modeling, architectural exploration, or system-level analysis.
• Ability to evaluate trade-offs using metrics such as performance-per-watt, energy per task, utilization, latency, throughput, and bandwidth.
• Experience modeling workloads or analyzing how workload characteristics affect system power and performance.
• Familiarity with silicon telemetry, performance-monitoring counters, power sensors, traces, logs, or lab measurement data.
• Strong data-analysis and debugging skills; ability to correlate multiple data sources and explain discrepancies.
• Experience designing maintainable software with clear interfaces, automated testing, documentation, and reproducible workflows.
• Demonstrated ownership of ambiguous technical areas and strong written and verbal communication to translate findings into recommendations.

Nice-to-have:

• Experience developing power or performance models for complex SoCs, CPUs, GPUs, AI accelerators, or automotive platforms.
• Knowledge of dynamic power management, DVFS, clock/power gating, thermal management, idle states, and workload-driven resource management.
• Familiarity with statistical modeling, machine learning, optimization, or sensitivity analysis applied to power-performance prediction.
• Proven ability to turn prototypes into reliable, widely adopted engineering platforms.

Education Requirements

Master's in Computer Engineering, Electrical Engineering, Computer Science, or a related STEM field — or equivalent practical experience.

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.