Description
The MLIL DataPlane team is hiring a Senior Software Development Engineer to design and implement the inference data plane for large language models on custom hardware. The role focuses on optimizing compute kernels, validating LLM architectures, integrating custom accelerator backends with serving frameworks, building test and profiling infrastructure, improving latency and throughput, and owning features end-to-end. The position requires a bachelor's degree in computer science or equivalent, at least seven years of full software development experience, strong C/C++ and Linux skills, and experience developing compute kernels for GPUs, DSPs, or custom accelerators. The role is based in Cupertino, California, with a base salary of 193,300 to 261,500 USD annually.
