Research Engineer - Geo-Distributed Inference
AI
Pluralis Research is seeking a Research Engineer for Geo-Distributed Inference to own and build the inference stack for Protocol Learning, training and serving large models on decentralized consumer hardware. The role involves designing novel algorithms for fast inference over the public internet and requires hands-on experience with serving systems and distributed inference research.
What you'll do
- Own the inference stack end-to-end: pipeline-parallel execution, placement and routing, transport, serving engine, and failure handling.
- Invent algorithms for fast inference on consumer hardware over the public internet.
- Serve training and users: keep rollout pipeline fast and reliable for RL training and turn it into serving layer for models.
What you need
Must-have
Serving-engine internalsLarge-scale inference systemsDistributed inferencePipeline parallelismLow-bandwidth networkingLLM serving systemsDecentralized training
Nice-to-have
Reinforcement Learning post-trainingApple siliconMLXP2P networkingNAT traversal
Soft skills
Mission alignmentComfortable working across timezonesProfessional-level English proficiency
Research EngineerGeo-Distributed InferenceProtocol LearningDecentralized AIInference SystemsDistributed SystemsMachine LearningRemoteFull-time