1 day ago
Base Salary
$184k - $357k/yr
Responsibilities
- Lead cross-layer efforts to improve LLM efficiency across model architecture, training, and inference systems.
- Analyze LLM workloads across GPUs, memory systems, interconnects, and distributed infrastructure to identify model-system-hardware co-design opportunities.
- Establish a measurement-driven efficiency roadmap and lead optimization projects from investigation through production deployment.
- Partner with model researchers, systems engineers, compiler and kernel developers, and hardware architects to shape model, software, and hardware roadmaps.
Requirements
- MS or PhD in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent experience.
- At least 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 involving model quality, computational cost, memory footprint, latency, throughput, and power.
- Strong background in performance analysis, roofline modeling, workload characterization, benchmarking, and hardware-aware optimization.
- Demonstrated technical leadership and experience driving complex optimization projects from concept to production.
- Preferred experience includes low-precision computation, quantization, sparsity, Mixture-of-Experts, long-context inference, speculative decoding, and co-designing models with training, inference, compiler, or hardware constraints.
Benefits
- Hybrid work arrangement.
- Equity and benefits are provided.
- Applications will be accepted at least until September 7, 2026.
Categories
About Nvidia
Since its founding in 1993, NVIDIA (NASDAQ: NVDA) has been a pioneer in accelerated computing. The company’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, ignited the era of modern AI and is fueling the creation of the metaverse. NVIDIA is now a full-stack computing company with data-center-scale offerings that are reshaping industry.