Remote RL Post-Training Scientist (Distributed ML)

Pluralis Research; Oregon; Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity-Heavy

Remote-first

Visa sponsorship & relocation

Global team

Job summary

Pluralis Research is hiring a senior RL post-training engineer to advance Protocol Learning and decentralized RL on consumer hardware. You will own end-to-end post-training stacks, from rollout ingestion to weight synchronization across geo-distributed workers.

You will design algorithms for asynchronous, high-latency environments, push first post-trained models to public artifacts, and collaborate with a global team.

Qualifications

• Hands-on RL post-training on large language models and systems integration.
• Strong engineering with production-quality Python and PyTorch.
• Publications or unpublished work in RL post-training or distributed RL.
• Mission alignment with Protocol Learning and decentralized AI.

Responsibilities

• Build the post-training stack end-to-end: rollout ingestion, reward computation, policy updates, and synchronized weights across the network.
• Invent algorithms for asynchronous, high-latency, partially trusted generation with efficient updates.
• Ship first post-trained models and establish evaluation and public artifacts.

Skills

RL post-training

Distributed systems

Python

PyTorch

Research experience

Tools

vLLM

SGLang

Job description

Pluralis Research is hiring a senior RL post-training engineer to advance Protocol Learning and decentralized RL on consumer hardware. You will own end-to-end post-training stacks, from rollout ingestion to weight synchronization across geo-distributed workers.

You will design algorithms for asynchronous, high-latency environments, push first post-trained models to public artifacts, and collaborate with a global team.