About this role
Member of Technical Staff, TPU Performance Engineering at Inferact. Location: Singapore. Role: optimizing backends, building integrations, benchmarking performance Requirements: Bachelor's or equivalent; hands-on experience optimizing TPU workloads with JAX, XLA, Pallas; deep understanding of TPU execution and memory; ML kernel and runtime optimization; strong profiling and benchmarking skills. Category: Engineering Seniority: Senior Level Tools: JAX, XLA, Pallas, vLLM, SGLang, TensorRT-LLM, MLIR, LLVM, PyTorch/XLA, TPU Commitment: Full Time Workplace: Onsite Languages: English