Research Engineer - Post-Training

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• Publications or defendable unpublished work in RL post-training or distributed RL.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 works on Protocol Learning: training and serving large models in a fully decentralized way on small consumer-grade devices connected via the internet. Despite being dismissed as infeasible, we have made significant advances on this problem, most recently Agora, a permissionless run that pretrained an 8B model from scratch on consumer GPUs spread over the internet, with no single participant ever holding the full weights (tech report). While many of the core research problems have been solved, Protocol Learning unlocks a series of new challenges. For the mission in full, read A Third Path: Protocol Learning. Agora gave us a pretrained 8B model. Post-training is how we make it useful for agentic use-cases. But every post-training stack you've seen assumes a datacenter — synchronous rollouts, fast interconnects, trusted workers. Ours gets none of that. It has to run on consumer GPUs, and Macs spread across the public internet, training a model whose weights no single participant ever holds, with rollouts arriving from a geo-distributed inference pipeline at high latencies. Your primary role is to make RL post-training work here anyway — the algorithms and the system, end-to-end.

Key Responsibilities

• 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.
• Invent the algorithms: Standard RL recipes assume on-policy rollouts from fast, trusted hardware. You adapt them to asynchronous, high-latency, partially trusted generation: staleness tolerance, off-policy corrections, and communication-efficient policy updates.
• Ship first post-trained models: You build the evals that show the models are improving, and you take the first decentralized post-trained release from run to public artifact.

What We're Looking For

• Hands-on RL post-training: You've run RL post-training on large language models — RLHF, RLVR, or reasoning-focused RL — and touched the systems layer yourself: rollout generation, async training loops, weight synchronization. Not just launched jobs on someone else's stack.
• 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.

Nice to Have

• Experience training over slow networks, or with decentralized or federated setups.
• Familiarity with serving-engine internals such as vLLM or SGLang — our rollout pipeline is a serving system.
• Experience with reward modeling or building verifiable-reward datasets.
• Experience with P2P networking and NAT traversal.
• Experience at proprietary, open-weight and open-source AI labs

Compensation & Benefits

• Equity-Heavy Package: We offer significant ownership for key technical contributors in addition to a high base salary.
• Remote-First Culture: Flexible work environment with team members distributed globally.
• Visa Sponsorship: Optional full visa sponsorship and relocation support to either Australia or the US.
• Open Problems: Training and serving frontier models on hardware you don't control, over networks you don't own, mostly has no published answers yet. You'll write some of the first ones.

FYI's

• We work remotely across the world, with the main teams in Australia and North America. You'll need to be comfortable working across timezones.
• Applicants must have professional-level English proficiency (written and spoken).
• Recruiters: we aren't looking for agency support at this time. We'll reach out if we need help.