Inference Stack Engineer (Fully Remote)

Pluralis Research; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Equity package

Remote-first team

Job summary

Pluralis Research is building Protocol Learning: training and serving large models in a fully decentralized way on small consumer-grade devices connected via the internet.

They recruit top engineers to own inference stacks end-to-end, with a remote-first culture and visa sponsorship options to Australia or the US. Join a world-class, deeply technical team backed by notable investors.

Job description

• Own the inference stack end-to-end, from pipeline-parallel execution to routing and failure handling.
• Invent algorithms that make inference fast on consumer hardware over the public internet.
• Serve both RL training rollouts and final models in a permissionless, trustless environment.

What We're Looking For:

• Shipped serving systems or built large-scale inference systems hands-on.
• Research ability evidenced by publications or unpublished work in distributed inference.
• Experience with low-bandwidth, high-latency networking on the public internet.
• Equity-heavy package with significant ownership in addition to high base salary.
• Remote-first culture with a globally distributed team.
• Optional full visa sponsorship and relocation support to Australia or the US.

Nice to Have:

• Familiarity with RL post-training and exposure to Apple silicon or MLX.
• Experience with P2P networking, NAT traversal, and open-weight AI labs.

Pluralis Research

Pluralis Research works on Protocol Learning: training and serving large models in a fully decentralized way on small consumer-grade devices connected via the internet. They are a world-class, deeply technical team backed by Union Square Ventures and other tier-1 investors.