Pluralis Research
Research Engineer - Geo-Distributed Inference
San Francisco +1 · Remote · Full-time · Posted Aug 31, 2026
- Location
- San Francisco
Australia - Visa sponsorship
- Full visa sponsorship and relocation support are available to Australia or the US.
About the job
Build and operate a fast, reliable inference pipeline for decentralized AI models running on consumer hardware over the public internet, supporting RL training and future model serving.
What you'll do
- Own the inference stack end-to-end, including execution, placement and routing, transport, serving, and failure handling.
- Design, validate, and deploy algorithms for inference across consumer hardware and public networks.
- Keep inference reliable for RL rollouts and develop it into a serving layer for trained models.
What they ask for
- Hands-on experience shipping serving-engine internals or building a large-scale inference system.
- Research ability in distributed inference or a related field, demonstrated through publications or work the candidate can explain.
- Professional-level written and spoken English.
- Alignment with the mission of Protocol Learning.
Nice to have
- Familiarity with RL post-training, Apple silicon, MLX, P2P networking, or NAT traversal.
- Experience at proprietary, open-weight, or open-source AI labs.
Tools
RL, Apple silicon, MLX, P2P networking, NAT traversal
AI focus
Develop distributed inference systems that generate RL training rollouts and serve trained models in a permissionless, trustless setting.
Model-written summary · the original posting is authoritative