Senior Inference Optimization ML Engineer

What you'll do

• Port and optimize models and kernels across accelerator backends, including embedded robot compute.
• Benchmark hardware and build performance, cost, and regression infrastructure.
• Apply model compression and validate numerical parity, policy quality, and robot-relevant behavior across backends.

What they ask for

• 2+ years of experience in inference optimization, ML systems, ML compilers, or a closely related field.
• Deep hands-on experience with PyTorch.
• Strong understanding of compute, memory, and interconnect bottlenecks across hardware architectures.
• Experience with model optimization techniques including quantization, distillation, pruning, and compilation.

Nice to have

• Experience optimizing inference for diffusion models.
• Production or deep project experience with an accelerator stack other than NVIDIA datacenter GPUs, or serious work deploying on consumer GPUs.

Tools

PyTorch, ROCm, HIP, MIOpen/hipBLASLt, Composable Kernel, XLA, JAX, Pallas

AI focus

Optimize inference for multimodal foundation models used in robotics, including vision, video, language, proprioception, and action models; work includes compression, backend portability, and real-time on-robot deployment.