Senior Modeling Architect, Performance Benchmarking

What you'll do

• Set and maintain benchmark methodology, workload definitions, and a reviewed internal benchmark suite across modeling fidelities and measured hardware.
• Bring up inference workloads and measure competitors end-to-end, reporting latency, throughput, and energy metrics.
• Document results, assumptions, configurations, and discrepancies; keep internal results separate from approved external claims.

What they ask for

• BS or MS in Computer Engineering, Electrical Engineering, Computer Science, or equivalent practical experience.
• 5+ years in GPU performance engineering, accelerator benchmarking, HPC performance measurement, or ML systems measurement.
• Experience building or operating benchmark harnesses that produce measured results on real GPUs or accelerators.
• Hands-on roofline, limiter, or analytical performance modeling; GPU profiling; Python; Linux; and cloud GPU operations.

Nice to have

• Experience correlating performance models or RTL/Verilator simulations against measured silicon or GPUs.
• GPU kernel work, inference-serving internals, distributed inference, or MLPerf/production inference benchmarking experience.

Pay

$210K – $250K USD base salary

Tools

Python, Linux, NVIDIA Nsight Systems, NVIDIA Nsight Compute, Hugging Face, vLLM, SGLang, TensorRT-LLM

AI focus

Benchmark AI inference workloads—including dense and MoE transformers and other workloads—to evaluate performance and energy for an optical inference accelerator.