AMD

Performance Engineer (Inference, Training & GPU)

AMD
Apply
17 hours ago

Base Salary

$172k - $258k/yr

Responsibilities

  • Optimize inference and production serving for latency, throughput, batching, caching, and scheduling.
  • Write and tune CUDA and Triton GPU kernels, including kernel fusion, memory and bandwidth optimization, and FP8/INT8 execution.
  • Improve training throughput and GPU utilization through parallelism, communication/compute overlap, mixed precision, and pipeline-stall elimination.
  • Build performance models, profiling workflows, and observability for throughput, latency, cost, and utilization.
  • Maintain numerical correctness across precision, kernel, and hardware changes.
  • Partner with researchers to productionize models and accelerate experiments.
  • Contribute to distributed systems supporting large-scale training and inference when needed.

Requirements

  • Strong performance-engineering foundations in profiling, roofline analysis, latency and throughput optimization, and root-cause investigation.
  • Deep GPU programming and optimization experience with CUDA and/or Triton.
  • Hands-on experience optimizing large-model inference and serving, including batching, KV/prompt caching, quantization, and low-latency sampling.
  • Hands-on experience optimizing training performance through parallelism, distributed communication, mixed or low precision, and utilization improvements.
  • Working knowledge of PyTorch and/or JAX internals and compiler paths such as torch.compile or XLA.
  • Strong Python proficiency with the ability to work in C++/CUDA, Rust, or Go as needed.
  • Preferred: experience at an AI lab or ML-native company, low-precision numerics, NCCL/NVLink and large-scale distributed systems, generative/diffusion/video/3D models, multiple accelerators, hardware-vendor collaboration, or GPU performance-modeling and observability frameworks.
AMD

About AMD

10,000+ employees

AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.

Contact me