LLM Efficiency Architect – Optimize Models & Compute

Thomas To

Santa Clara (CA)

On-site

USD 184,000 - 357,000

Full time

2 days ago

Be an early applicant

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Santa Clara is seeking a strong technical leader to drive a unified strategy for making LLMs more efficient from research through deployment. You will lead cross‑discipline efforts across model innovation, systems, and hardware awareness to ensure new capabilities fit compute, memory, power, and cost constraints.

The ideal candidate is hands‑on, identifies bottlenecks, and translates research ideas into scalable, real‑world improvements.

Qualifications

MS or PhD in Computer Science, Electrical Engineering, Computer Engineering, or related field.
5+ years of AI systems, model architecture, computer architecture, HPC, or performance optimization.
Strong understanding of LLM architectures, training and inference workloads, and tradeoffs between quality, cost, memory, latency, throughput, and power.
Background in performance analysis, roofline modeling, workload characterization, benchmarking, and hardware-aware optimization.

Responsibilities

Lead cross-layer efforts to improve LLM efficiency across model architecture, training and inference systems.
Analyze how LLM workloads map to GPUs, memory systems, interconnects, and distributed infrastructure for co-design opportunities.
Establish a measurement-driven efficiency roadmap and lead projects from investigation through production deployment.
Partner with researchers, systems engineers, compiler/kernel developers, and hardware architects on roadmaps.