Senior AI Training Performance Architect | Impact & Equity

NVIDIA; Santa Clara (CA); On-site; USD 184,000 - 356,500; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Senior AI Training Performance Architect to push the limits of AI training performance across hardware and software stacks. The role involves profiling, bottleneck analysis, and implementing production-quality software across the NVIDIA DL stack.

You'll work on MLPerf submissions and architecture studies, leveraging C++, Python, and CUDA to optimize workloads. The base salary bands reflect Level 4 and Level 5 roles, with equity and benefits available.

Qualifications

• PhD in CS, EE or CSEE (or equivalent) with 5+ years of experience; or MS with 8+ years of experience.
• Strong background in deep learning and neural networks, particularly in training.
• Solid understanding of computer architecture and GPU architecture fundamentals.
• Proven background in analyzing and tuning application performance.
• Proven experience with processor and system-level performance modeling.
• Proficiency in programming with C++, Python, and CUDA.

Responsibilities

• Understand, analyze, profile, and optimize AI training workloads on state-of-the-art hardware and software platforms.
• Identify performance bottlenecks of AI training on GPUs, prioritize and solve problems across key workloads.
• Implement production-quality software across multiple layers of NVIDIA's deep learning platform stack, from drivers to DL frameworks.
• Build and support NVIDIA submissions for MLPerf Training benchmarks.
• Implement key DL training workloads in NVIDIA's proprietary processor and system simulators to enable future architecture studies.
• Develop tools to automate workload analysis, optimization, and other critical workflows.

Skills

Deep learning

Neural networks

C++

Python

CUDA

GPU architecture

Education

PhD in CS/EE/CSEE

MS in CS/EE/CSEE

Job description

NVIDIA is seeking a Senior AI Training Performance Architect to push the limits of AI training performance across hardware and software stacks. The role involves profiling, bottleneck analysis, and implementing production-quality software across the NVIDIA DL stack.

You'll work on MLPerf submissions and architecture studies, leveraging C++, Python, and CUDA to optimize workloads. The base salary bands reflect Level 4 and Level 5 roles, with equity and benefits available.