About this role
Member of Technical Staff, AMD GPU Performance Engineering at Inferact. Location: San Francisco, California, United States. Role: building backends, optimizing kernels, profiling benchmarks Requirements: Bachelor's or equivalent experience; hands-on AMD GPU optimization using ROCm/HIP/Triton/CK/AITER; deep understanding of AMD GPU execution, memory, toolchains; experience optimizing ML kernels and strong profiling/benchmarking skills. Category: Engineering Seniority: Senior Level Tools: ROCm, HIP, Triton, CK, AITER, vLLM, SGLang, TensorRT-LLM, MLIR, LLVM, PyTorch Commitment: Full Time Workplace: Onsite Languages: English