Neural Network Optimization Engineer

A Neural Network Optimization Engineer at Recraft is responsible for enhancing the performance, latency, and throughput of neural network inference workflows. This role involves optimizing models through techniques such as model quantization and utilizing tools like TensorRT and Triton, as well as collaborating closely with machine learning researchers to ensure efficient production deployments. The engineer will also benchmark and analyze performance on various hardware platforms while staying abreast of advancements in model optimization technologies.