Remote RL Post-Training Engineer — Decentralized AI

Pluralis Research; California; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Equity-Heavy Package

Remote-First Culture

Visa Sponsorship & Relocation

Job summary

Pluralis Research is seeking an engineer to advance Protocol Learning by building and refining the RL post-training stack. You will handle rollout ingestion, reward computation, and weight synchronization across a geo-distributed setup.

The role emphasizes production-grade Python and PyTorch, with an expectation of publishing results or defending ongoing work. A remote-first team collaborates across time zones and international locations.

Qualifications

• Hands-on RL post-training on large language models with system exposure.
• Strong production-quality Python and PyTorch experience.
• Publications or defendable unpublished work in RL post-training or distributed RL.

Responsibilities

• Build the post-training stack end-to-end: rollout ingestion, reward computation, policy updates, weight propagation.
• Invent algorithms for asynchronous, high-latency, partially trusted generation with off-policy corrections.
• Ship first post-trained models and establish evaluations leading to public artifacts.

Skills

RL post-training

Python

PyTorch

Distributed systems

Asynchronous training

Weight synchronization

Experiment automation

Tools

vLLM

SGLang

Job description

Pluralis Research is seeking an engineer to advance Protocol Learning by building and refining the RL post-training stack. You will handle rollout ingestion, reward computation, and weight synchronization across a geo-distributed setup.

The role emphasizes production-grade Python and PyTorch, with an expectation of publishing results or defending ongoing work. A remote-first team collaborates across time zones and international locations.