Quick overview
Job description
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 execution, and serving infrastructure.
What You'll Do
Optimize GPU and system performance for training and inference workloads.
Profile and remove bottlenecks across kernels, memory, systems, and clusters using Nsight and related tools.
Implement low-level 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, InfiniBand, RoCE, and disaggregated serving approaches.
Build benchmarks and regression tests to sustain performance improvements 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, or distributed systems, with hands-on ML systems or GPU performance experience in a current or recent role.
Experience authoring core features in an inference or training framework such as vLLM, SGLang, TensorRT-LLM, or Megatron, rather than focusing only on deployment or integration.
Direct kernel development experience on NVIDIA GPUs using CUDA, CUTLASS, Triton, or PTX.
Strong machine learning and computer science fundamentals, with a degree in computer science or a related quantitative field.
Experience with inference or training performance, including GPU kernels, runtimes, or distributed execution.
Experience optimizing diffusion, video, image, or other multimodal workloads is relevant.
Compensation & Benefits
Base salary: $180,000 to $260,000 annually. Visa sponsorship is available.
Location
On-site in Menlo Park, California.
Haystack's AI agent can fill in and submit this application for you. How AI auto apply works
Will your resume get past this employer's screening? Check your resume against this job, free