Senior LLM Efficiency Architect — Model-System Optimizer

NVIDIA; Santa Clara (CA); Hybrid; USD 184,000 - 357,000; Full time

Job summary

NVIDIA is seeking a strong technical leader to drive a unified strategy for making LLMs more efficient from research through deployment. You will lead a multidisciplinary effort combining model ideas, systems expertise and hardware awareness to deliver scalable improvements while managing compute, memory, power and cost constraints.

The role requires hands-on leadership across model, software and hardware roadmaps, with a focus on measurable throughput and cost-per-token improvements.

Qualifications

• Advanced degree or equivalent in CS/EE or related field.
• Strong background in AI systems and model architectures.
• Proven track record in performance optimization and HPC.

Responsibilities

• Lead cross-layer efforts to improve LLM efficiency across architecture, training and inference.
• Analyze workloads mapping to GPUs, memory, interconnects and distributed systems.
• Establish measurement-driven roadmaps from research to production.
• Collaborate with researchers, engineers, compilers and hardware architects.

Skills

AI systems

Model architecture

High-performance computing

Hardware awareness

Performance optimization

Education

MS or PhD degree or equivalent

Job description

NVIDIA is seeking a strong technical leader to drive a unified strategy for making LLMs more efficient from research through deployment. You will lead a multidisciplinary effort combining model ideas, systems expertise and hardware awareness to deliver scalable improvements while managing compute, memory, power and cost constraints.

The role requires hands-on leadership across model, software and hardware roadmaps, with a focus on measurable throughput and cost-per-token improvements.