24 hours ago
Base Salary
$272k - $431k/yr
Responsibilities
- Drive end-to-end performance characterization workstreams with CSP and hyperscale engineering teams.
- Gather and synthesize customer performance feedback and champion optimization priorities across CUDA, NCCL, driver, and firmware teams.
- Update and validate STREAM, GPU Burn, and GPU BLAST for current NVIDIA rack-scale systems, GPU architectures, and CPU platforms.
- Partner with CSPs on profiling infrastructure, benchmark harnesses, configuration validation, and deployment readiness.
- Compare performance across CSP deployments and identify configuration, software, or workload causes of performance gaps.
- Define performance validation test strategies and tooling requirements for NVIDIA certification and customer acceptance.
- Communicate performance findings to technical audiences and executive leadership while influencing multiple engineering teams.
Requirements
- 15+ years of experience in systems performance engineering, ideally in GPU, HPC, or ML infrastructure.
- Bachelor's or master's degree in Computer Science, Computer Engineering, or a related field, or equivalent experience.
- Proficiency with GPU workload profiling using Nsight Systems, Nsight Compute, DCGM metrics, or equivalent instrumentation.
- Understanding of distributed training performance, including computation and communication overlap, pipeline bubbles, memory bandwidth utilization, and collective efficiency.
- Knowledge of statistical performance analysis, including regression detection, confidence intervals, and large-scale A/B comparisons.
- Understanding of software-stack performance factors including driver overhead, collective algorithm selection, memory allocation, scheduling, and firmware power management.
- Strong Python, pandas, data analysis, visualization, and dashboard skills.
- Demonstrated ability to influence multiple engineering teams and communicate effectively with technical and executive audiences.
- Preferred experience with Megatron-LM, DeepSpeed, FSDP, CSP or hyperscaler ML infrastructure, NVIDIA DGX, NVIDIA HGX, NVLink topology, automated performance regression detection, vLLM, TensorRT-LLM, SGLang, and continuous batching.
Benefits
- Base salary range is USD 272,000–431,250, determined by location, experience, and other objective job-related factors.
- Eligible for equity and benefits.
- Applications are accepted at least until November 11, 2026; the posting is for an existing vacancy.
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.