Member of Technical Staff, ML Systems

About the Role

Join an AI team building high-performance training and inference systems for image, video, and world-model workloads. You will improve efficiency across GPU kernels, distributed engines, and multi-node systems, helping make advanced models faster to train and serve.

What You'll Do

• Optimize system and GPU performance for training and inference across image, video, and world-model workloads.

• Use Nsight and related tools to identify and remove kernel, memory, system, and cluster bottlenecks.

• Implement low-level optimizations using CUDA and Triton.

• Design and improve distributed inference and training engines for diffusion models.

• Improve communication performance across GPUs and nodes using NCCL, RDMA, InfiniBand, RoCE, and disaggregated serving techniques.

• Build benchmarking and regression harnesses to maintain performance gains in production.

• Co-design kernels, runtimes, and models with hardware characteristics in mind.

What We're Looking For

• At least 2 years of experience in deep learning training or inference systems, GPU performance, or distributed systems, including 1 or more years of hands-on ML systems or GPU performance work in a recent full-time role.

• Experience authoring core features in an inference or training framework, such as vLLM, SGLang, TensorRT-LLM, Megatron, or a comparable system.

• Hands-on experience writing kernels for NVIDIA GPUs using CUDA, CUTLASS, Triton, or PTX.

• Strong machine learning and computer science fundamentals, supported by a degree in computer science or a related quantitative field.

• Experience optimizing inference or training performance, including GPU kernels, runtimes, or distributed execution.

• Experience with PyTorch, Nsight, NCCL, and RDMA, and familiarity with diffusion, video, image, or other multimodal workloads.

Compensation & Benefits

Base salary is $180,000 to $260,000 USD annually. Visa sponsorship is available.

Location

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