Senior Modeling Architect, Performance Benchmarking - Austin, Texas, United States

Originally posted 4 September 2026 by the employer — open 17 days.

About the role

This role is responsible for owning the benchmarking numbers for the T100 optical inference accelerator.

What you'll do

• Own performance and energy metrics across modeling fidelities and measured hardware.
• Produce numbers for workloads across roofline and limiter models, architecture performance models, RTL simulation, and measured competitor hardware.
• Bring up inference workloads from Hugging Face, PyTorch, and vendor stacks such as vLLM, SGLang, TensorRT-LLM, and Triton Inference Server.
• Measure competing GPUs and accelerators end-to-end, managing cloud/lab accounts, images, drivers, and run recipes.
• Report time to first token (TTFT), inter-token latency (ITL), tokens per second, tokens per second per watt, and energy using nvidia-smi, DCGM, or power capping.
• Document disagreements between RTL simulation, performance models, and measured competitor results.

What you'll need

• BS or MS in Computer Engineering, Electrical Engineering, Computer Science, or equivalent practical experience.
• 5+ years of experience in GPU performance engineering, accelerator benchmarking, HPC performance measurement, or ML systems measurement.
• Track record of building or operating benchmark harnesses that produced measured results on GPUs or accelerators.
• Hands-on experience with roofline analysis, limiter analysis, or analytical performance modeling.
• GPU performance analysis with NVIDIA Nsight Systems and Nsight Compute, covering HBM-bound versus compute-bound analysis, precision (FP16, BF16, FP8, INT8), and batching.
• Working knowledge of LLM inference stacks such as Hugging Face, vLLM, SGLang, or TensorRT-LLM, including prefill versus decode, continuous batching, and MoE.
• Proficiency in Python for harnesses, parsing, and plots, and comfort working in Linux.
• Cloud GPU operations on AWS, GCP, or Azure, including containers, instance types, drivers, quotas, and cost.

Nice to have

• Experience correlating a performance model or RTL/Verilator simulation against measured silicon or GPUs.
• GPU kernel work in CUDA, CUTLASS, or Triton, or familiarity with PyTorch internals.
• Familiarity with current inference-serving internals such as PagedAttention, FlashAttention, speculative decoding, and disaggregated prefill.
• Distributed inference experience covering collectives, all-reduce, NCCL, NVLink, and InfiniBand, or work with MLPerf or production inference benchmarking pipelines.

Skills: performance benchmarking, AI inference accelerator, silicon photonics, GPU performance engineering, LLM inference stacks