LLM Efficiency Architect — Lead Cross‑Layer Optimization (Equity)

NVIDIA AI; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Santa Clara, CA seeks a strong technical leader to drive a unified strategy for making LLMs more efficient from research through deployment.

You will lead cross‑layer optimization across model architecture, training and inference, ensuring scalable, real‑world improvements while collaborating with researchers, engineers, compiler and hardware teams. Equity and a competitive base salary are offered, with Level 4 or Level 5 placement.

Qualifications

• MS or PhD degree or equivalent experience in a related field.
• 5+ years of relevant experience in AI systems, model architecture, computer architecture, high-performance computing, or performance optimization.
• Strong understanding of LLM architectures, training and inference workloads and tradeoffs among quality, cost, memory, latency and power.
• Strong background in performance analysis, roofline modeling, workload characterization, benchmarking and hardware-aware optimization.
• Proven ability to provide technical leadership and drive complex optimization projects from concept to production.

Responsibilities

• Lead cross-layer efforts to improve efficiency of large language models across architecture, training and inference systems.
• Analyze LLM workloads mapping to GPUs, memory systems, interconnects and distributed infrastructure for co-design opportunities.
• Establish a measurement-driven efficiency roadmap and lead projects from investigation to production deployment.
• Partner with model researchers, systems engineers, compiler and kernel developers, and hardware architects to influence future roadmaps.

Skills

AI systems

Model architecture

High-performance computing

Performance optimization

Technical leadership

Education

MS or PhD

Tools

Benchmarking

Performance analysis tools

Job description

NVIDIA in Santa Clara, CA seeks a strong technical leader to drive a unified strategy for making LLMs more efficient from research through deployment.

You will lead cross‑layer optimization across model architecture, training and inference, ensuring scalable, real‑world improvements while collaborating with researchers, engineers, compiler and hardware teams. Equity and a competitive base salary are offered, with Level 4 or Level 5 placement.