Research Scientist - Geo-Distributed Inference
Pluralis Research is a research lab developing decentralized AI through Protocol Learning, a communication-efficient approach to collaborative model training. It operates open training systems that allow distributed contributors to provide compute for collectively owned foundation models.
Funding history
About Pluralis Research
Pluralis Research develops Protocol Learning, which enables foundation models to be trained and served across globally distributed participants without requiring a single participant to hold the complete model. Its work covers low-bandwidth model parallelism, asynchronous distributed optimization, fault-tolerant training, privacy-preserving unextractable models, and collective ownership. The organization operates Agora and Node0 training systems, publishes research, provides participation documentation, and releases open-source software for distributed training and reinforcement-learning workflows.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build and own the inference stack end to end, including pipeline-parallel execution, placement and routing, transport, serving, and failure handling. You will invent and validate methods for fast inference on consumer hardware over the public internet, then put them into production. You will keep the rollout pipeline reliable for reinforcement-learning training and develop it into a serving layer for trained models.
Requirements
- Have shipped serving-engine internals or built a large-scale inference system
- Demonstrate research ability in distributed inference or a related field
- Have experience with low-bandwidth, high-latency networking environments
- Have professional-level written and spoken English proficiency
- Be comfortable working across time zones
Responsibilities
- Build and own the end-to-end inference stack, including pipeline-parallel execution, placement and routing, transport, serving, and failure handling
- Design, validate, and productionize algorithms for fast inference on consumer hardware over the public internet
- Keep the rollout pipeline fast and reliable for reinforcement-learning training
- Develop the inference pipeline into the serving layer for trained models
Benefits
- Significant equity in addition to a high base salary
- Flexible remote-first work environment
- Optional full visa sponsorship and relocation support to Australia or the US