Member of Technical Staff, ML Systems

Join an AI systems team building high-performance training and inference infrastructure for image, video, and world-model workloads. You will improve speed and efficiency across GPU kernels, distributed execution, and serving systems.

Optimize training and inference performance for image, video, and world-model workloads. Profile bottlenecks at kernel, memory, system, and cluster levels using Nsight and related tools. Implement low-level GPU optimizations with CUDA and Triton. Design and improve distributed training and inference engines for diffusion models. Improve communication performance across GPUs and nodes using NCCL, RDMA, Infini Band, or RoCE. Build benchmarking and regression tools to maintain performance gains in production.

Coordinate hardware, runtime, kernel, and model design for efficient execution.

At least 2 years of experience in deep learning training or inference systems, or distributed systems, including hands-on ML systems or GPU performance work. Experience optimizing inference or training performance through GPU kernels, runtime systems, or distributed execution. Direct experience writing kernels for NVIDIA GPUs using CUDA, CUTLASS, Triton, or PTX. Authored core features in a training or inference framework, such as vLLM, SGLang, TensorRT-LLM, or Megatron, rather than focusing only on deployment or integration.

Strong machine learning and computer science fundamentals, with a degree in computer science or a related quantitative field. Experience with PyTorch, Nsight, and workloads such as diffusion, video, image, or other multimodal models is relevant. Compensation & Benefits Base

$180,000 to $230,000 annually. Visa sponsorship is available.

On-site in Menlo Park, California, United States.