Remote Research Scientist, Geo-Distributed Inference

pluralis-research; United States; Remote; USD 180,000 - 280,000; Full time

Benefits offered by this job

Equity-Heavy Package

Remote-First Culture

Visa Sponsorship & Relocation to US

Job summary

Pluralis Research is pioneering Protocol Learning, training and serving large models in a decentralized setup across consumer GPUs worldwide. We seek engineers who can own the end-to-end inference stack, invent fast algorithms for distributed serving, and maintain reliable pipelines for RL training and post-training serving across time zones.

We offer an equity-heavy package and a remote-first culture with visa sponsorship and relocation options to the US.

Qualifications

• Shipped serving-engine internals or large-scale inference systems.
• Publications or blog posts in distributed inference or nearby fields.
• Experience with networks and systems designed for high latency/low bandwidth.

Responsibilities

• Own the inference stack end-to-end: pipeline-parallel execution, placement and routing, transport, serving engine, failure handling.
• Invent algorithms to speed inference on consumer hardware via internet, validating and deploying them.
• Serve training and users: maintain fast rollout pipelines for RL training and adapt to serving later.

Skills

Shipped serving systems

Research publications

Low-bandwidth networking

Mission alignment

P2P networking

Tools

Distributed inference

LLM serving systems

Job description

Pluralis Research is pioneering Protocol Learning, training and serving large models in a decentralized setup across consumer GPUs worldwide. We seek engineers who can own the end-to-end inference stack, invent fast algorithms for distributed serving, and maintain reliable pipelines for RL training and post-training serving across time zones.

We offer an equity-heavy package and a remote-first culture with visa sponsorship and relocation options to the US.