Research Engineer: Decentralized Inference & Protocol Learning

Pluralis-Research; San Francisco (CA); Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity-Heavy Package

Remote-First Culture

Visa Sponsorship

Open Problems

Job summary

Pluralis Research seeks a senior engineer to own the inference stack end-to-end, building fast, reliable systems for decentralized RL workloads on consumer hardware. The role emphasizes hands-on delivery of serving-engine components and novel algorithms to speed inference over the public internet.

The candidate will contribute to training rollouts and adapt the serving layer for models as they move from training to production, while aligning with the Protocol Learning mission and remote-first

Qualifications

• Shipped serving systems or large-scale inference engines.
• Publications or blog posts in distributed inference or related fields.
• Experience with low-bandwidth, high-latency environments such as the public internet.
• Belief that Protocol Learning represents a viable path for sovereign AI.

Responsibilities

• Own the inference stack end-to-end, including pipeline-parallel execution and serving engine responsibilities.
• Invent algorithms to speed inference on consumer hardware over the public internet.
• Support training rollouts and evolve the serving layer for deployed models.

Skills

Shipped serving systems

Research publications

Low-bandwidth networking

Mission alignment

Job description

Pluralis Research seeks a senior engineer to own the inference stack end-to-end, building fast, reliable systems for decentralized RL workloads on consumer hardware. The role emphasizes hands-on delivery of serving-engine components and novel algorithms to speed inference over the public internet.

The candidate will contribute to training rollouts and adapt the serving layer for models as they move from training to production, while aligning with the Protocol Learning mission and remote-first