Senior Deep Learning Performance Architect

Job Title

Senior Deep Learning Performance Architect

Role Summary

Design and evaluate hardware and system-level architectures to accelerate deep learning and high-performance computing workloads. The role sits on the Deep Learning Architecture team and partners with software, systems, and product teams to align hardware capabilities with real-world workload requirements.

Experience Level

Senior — 5+ years of hands-on experience in GPU/ASIC architecture, parallel computing, or system performance engineering.

Responsibilities

Own analysis, modeling, and evaluation of production AI workloads to drive architecture and product decisions.

• Design and evaluate hardware architectures to improve performance, efficiency, and scalability for production AI workloads.
• Analyze and optimize large-scale deep learning workloads, including LLM inference and training in real-world deployments.
• Build and use performance and power models (Python/C++) to inform architecture trade-offs.
• Identify and resolve bottlenecks across compute, memory, and interconnect subsystems.
• Evaluate PPA (performance, power, area) trade-offs and guide feature prioritization for next-generation GPU/ASIC designs.
• Collaborate closely with software, systems, and product teams to ensure hardware meets workload needs.

Requirements

Must-have technical skills and experience.

• 5+ years of hands-on experience in GPU/ASIC architecture, parallel computing, or system performance engineering.
• Experience with deep learning workloads in production (training and/or inference).
• Proficiency in Python and C++ for building performance models, simulators, or analysis tools.
• Solid understanding of system architecture: memory hierarchy, data movement, and scalability.
• Experience debugging, profiling, and performance tuning on real systems.
• Proven ability to work across teams and drive technical decisions in fast-paced product environments.

Nice-to-have:

• Experience translating workload behavior into concrete hardware or system-level improvements.
• Practical experience with LLM inference optimization (batching, disaggregation, KV-cache management, latency/throughput tuning).
• Familiarity with production inference systems (scheduling, multi-node scaling, resource utilization).

Education Requirements

MS or PhD in Computer Science, Electrical Engineering, Computer Engineering, or a related technical 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.