Research Engineer 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.

Distributed
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.

View jobs by Pluralis Research

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 a geo-distributed inference stack, including pipeline-parallel execution, placement, routing, transport, serving, and failure handling. You will develop and validate new algorithms for consumer hardware and keep inference reliable for RL rollouts and model serving.

Requirements

  • Experience shipping serving-engine internals or building a large-scale inference system
  • Research publications or demonstrable work in distributed inference LLM serving pipeline parallelism or decentralized training
  • Experience with low-bandwidth high-latency networking
  • Professional-level written and spoken English proficiency

Responsibilities

  • Build and own the inference stack including pipeline-parallel execution placement routing transport serving and failure handling
  • Design validate and productionize inference algorithms for consumer hardware and public networks
  • Maintain a fast reliable rollout pipeline for RL training and model serving

Benefits

  • Equity-heavy compensation package
  • Flexible remote-first work environment
  • Optional visa sponsorship and relocation support to Australia or the US