Jobs → Engineering → Machine Learning Systems Engineer

About the Role We are seeking an experienced Machine Learning Systems Engineer to focus on optimizing LLM inference performance on AWS Trainium. Key Responsibilities • Optimize LLM inference latency, throughput, and cost across AI accelerator platforms • Work with AWS Trainium/Trainium2/Trainium3 and AWS Neuron SDK • Implement Speculative Decoding, MTP, and other advanced techniques Requirements • 10+ years of experience in machine learning systems engineering • Strong expertise in Python and PyTorch • Experience with LLM Inference Optimization and vLLM • Knowledge of CUDA, Triton, NKI, and Performance Benchmarking