Similar Jobs
See allMember of Technical Staff, Post-Training
Cohere
Global
Reinforcement Learning
Large Language Models
Python
Research Scientist
Pluralis Research
Global
PyTorch
Distributed Training
Python
Inference Stack Engineer
Pluralis Research
Global
Distributed Systems
Research Data Scientist
Binance
Asia
Python
PyTorch
Machine Learning
AI Research Engineer
Niural
Global
Python
Reinforcement Learning
Machine Learning
About Pluralis:
- We are building Protocol Learning, a decentralized path to training and serving frontier models on consumer-grade hardware.
- We are a small, deeply technical team backed by tier-1 investors, with a remote-first global culture.
The Role:
- You will own the post-training stack end-to-end, from rollout ingestion to policy updates and weight distribution.
- You will adapt RL algorithms to asynchronous, high-latency, partially trusted generation.
- You will ship the first decentralized post-trained models, including evals and public artifacts.
What We're Looking For:
- Hands-on experience running RL post-training on large language models and touching the systems layer yourself.
- Production-quality Python and PyTorch skills, with an emphasis on concurrency and failure handling.
- Research ability demonstrated through publications or unpublished work you can defend in detail.
Compensation & Benefits:
- Equity-heavy package with significant ownership for key technical contributors.
- Remote-first culture with flexible working across the world.
- Optional full visa sponsorship and relocation support to Australia or the US.
Pluralis Research
Pluralis Research is developing Protocol Learning, a decentralized approach to training and serving large models on consumer devices. We are a small, deeply technical team backed by Union Square Ventures, with a remote-first culture and team members spread globally.