Remote Research Engineer - Decentralized Inference Systems

Pluralis Research; California; Remote; USD 180,000 - 280,000; Full time

Benefits offered by this job

Equity-heavy package

Remote-first culture

Visa sponsorship & relocation to AU/US

Open research challenges

Job summary

Pluralis Research is advancing Protocol Learning by training and serving large models in a fully decentralized way on consumer devices connected via the internet.

We are a remote-first team with equity-heavy compensation, visa sponsorship, and relocation support to Australia or the US. You will own the end-to-end inference stack, invent new algorithms, and help serve training and deployed models in production.

Qualifications

• Shipped serving-engine internals or built large-scale inference systems hands-on.
• Publications or blogposts in distributed inference or nearby fields are strong signals.
• Experience working in low-bandwidth, high-latency networks is valuable.
• Alignment with Protocol Learning and the mission of a decentralized AI path.

Responsibilities

• Own the inference stack end-to-end: planning, placement, routing, transport, serving, and failure handling.
• Invent new algorithms to speed inference on consumer hardware over the internet.
• Support both training rollout pipelines and the serving layer for trained models.

Skills

Distributed systems

LLM serving

P2P networking

Tools

GPU clusters

Job description

Pluralis Research is advancing Protocol Learning by training and serving large models in a fully decentralized way on consumer devices connected via the internet.

We are a remote-first team with equity-heavy compensation, visa sponsorship, and relocation support to Australia or the US. You will own the end-to-end inference stack, invent new algorithms, and help serve training and deployed models in production.