16 Oct
|
Pluralis Research
|
Sydney
16 Oct
Pluralis Research
Sydney
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.
#J-18808-Ljbffr
📌 Remote RL Post-Training Research Engineer (Sydney)
🏢 Pluralis Research
📍 Sydney