Distributed Inference Systems Engineer

Pluralis Research is exploring Protocol Learning to train and serve large models in a fully decentralized way across consumer hardware and the public internet. The role centers on building end-to-end inference stacks, deploying novel algorithms for fast inference on consumer GPUs, and ensuring scalable, robust pipelines for RL training and model serving. We value candidates with experience shipping serving-engine internals, a track record in distributed inference research, and a strong alignment