Pluralis Research is seeking an engineer to advance RL post-training for large language models in a decentralized setting. You will develop the end-to-end post-training stack, handle asynchronous training loops, and contribute to evaluating released models across a global, remote-first team. The role emphasizes Python and PyTorch proficiency, distributed systems thinking, and a research-oriented mindset, with participation in cutting-edge protocols learning initiatives.
📌 Remote RL Post-Training Research Engineer (Townsville City)
🏢 Pluralis Research
📍 Townsville City
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.