At a Glance
- Tasks: Build and optimise post-training stacks for decentralised AI systems.
- Company: Join Pluralis Research, a leader in innovative AI solutions.
- Benefits: Enjoy remote work flexibility and global collaboration.
- Other info: Work in a dynamic, research-focused environment with global impact.
- Why this job: Shape the future of AI with cutting-edge algorithms and systems.
- Qualifications: Strong experience in RL post-training and Python/PyTorch.
The predicted salary is between 121500 - 148500 $ per year.
Pluralis Research is seeking a seasoned RL post-training engineer to build the end-to-end post-training stack, from rollout ingestion to policy updates and weight synchronization across a geo-distributed network.
You’ll shape algorithms and systems to make decentralized, asynchronous post-training work at scale.
We value hands-on RL post-training, strong Python/Py Torch engineering, and a research mindset. This is a remote-first role with global collaboration across time zones.
#J-18808-Ljbffr
Remote RL Post-Training Engineer in Sydney employer: Pluralis Research
At Pluralis Research, we pride ourselves on being a remote-first AI startup that fosters a dynamic and innovative work culture. Our Operations Associate role not only provides the opportunity to collaborate closely with our leadership team but also encourages personal and professional growth through exposure to diverse operational projects. With a commitment to leveraging cutting-edge AI tools, we empower our employees to streamline workflows and contribute meaningfully to our mission of building a decentralised AI ecosystem.
