Pluralis Research is pioneering Protocol Learning and distributed post-training of large language models. You will build end-to-end RL post-training stacks on consumer hardware and public internet, turning research advances into real-world systems.
The role blends engineering, algorithm design, and research communication in a globally distributed setup. You will work across RLHF/RLVR with asynchronous, high-latency pipelines, contributing to the first decentralized post-trained releases and
J-*-Ljbffr
📌 Distributed Rl Post Training Engineer Brisbane
🏢 Pluralis Research
📍 Brisbane
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.