16 Oct
|
Pluralis Research
|
Canberra
16 Oct
Pluralis Research
Canberra
Pluralis Research is pioneering Protocol Learning and invites exceptional ML researchers to join the RL post-training effort. You will architect end-to-end post-training stacks, from rollout ingestion to weight synchronization, and drive the first decentralized post-trained releases.
You will work on asynchronous, high-latency systems, develop algorithms, and contribute to publication-worthy research while aligning with the mission of Protocol Learning and distributed AI.
#J-18808-Ljbffr
📌 Remote RL Post-Training Engineer for Decentralized AI (Canberra)
🏢 Pluralis Research
📍 Canberra