Staff Engineer, Inference Optimizations

Design and lead performance optimization for AI inference at the inference engine and GPU kernel layers. Drive benchmarking and architectural decisions to maximize throughput and minimize latency for large-model inference, including attention, memory/precision, kernel fusion, and distributed multi-node parallelization. Act as an IC leader and subject-matter expert across NVIDIA/AMD stacks (CUDA/ROCm/TensorRT/Triton), quantization (FP8/INT8/FP4), and open-source AI integration while partnering with Product/TPMs to ship developer-friendly capabilities.