Jobs

Inferact is seeking a TPU Performance Engineer to join their Research & Engineering team, focusing on optimizing vLLM for Google TPUs. In this role, you will build and optimize TPU backends, compiler integrations, and benchmarking infrastructure using technologies like JAX, XLA, and Pallas. The ideal candidate will have hands-on experience with TPU workloads, a deep understanding of TPU execution, and strong performance profiling skills. This position is crucial for making vLLM a first-class inference engine on TPU hardware, ensuring fast, benchmarked, and maintainable TPU support.