We’re searching for Staff Compiler Engineers to architect and build the ML backend (compiler, run-time, and debugger) for our next-generation OPTUs. You will own integration with PyTorch, Tensorflow, JAX, and MXNet down to our low-level kernel drivers. Your mission will be to create seamless support for a broad ecosystem of large AI models, and ensure we are pushing the limits of their performance envelope by closely partnering with hardware and modelling teams to understand device trade-offs.