# Research Engineer - Post-Training at Pluralis

- Company: Pluralis
- What the company does: Pluralis Research works on Protocol Learning — decentralized, communication-efficient model-parallel training for foundation models. Backed by USV.
- Company website: https://pluralis.ai/
- Type: Startups (AI role)
- Level: Mid level
- Location: San Francisco
- Work setup: Remote
- Posted: 2026-08-31
- Apply by: 2026-10-15
- Apply: https://jobs.ashbyhq.com/pluralis-research/37a272e7-f55c-42e6-8db8-5c94f9934d86
- Page: https://www.1752.vc/careers/jobs/pluralis-research-engineer-post-training/

## About the role

Build the post-training stack : You build the RL training loop end-to-end: rollout ingestion from the geo-distributed inference pipeline, reward computation, policy updates, and getting updated weights back out to the network. You set the direction, and you make things happen.

## What they're looking for

- Strong engineering : Production-quality Python and PyTorch: concurrency, failure handling, profiling before optimizing
- Research ability : Publications in RL post-training, asynchronous or distributed RL, or nearby fields are a strong signal. So is unpublished work you can defend in detail
- Mission alignment : You believe Protocol Learning is the viable third path for collective, trustless, and sovereign AI

Tags: Research