Research Scientist - Post-Training
pluralis researchMillbrae (CA)
Research Scientist - Post-Training
Posted today
pluralis researchMillbrae (CA)
SENIORITY
Senior
About the role
Protocol Learning Research Scientist 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'sWe 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.
We are backed by Union Square Ventures and other tier-1 investors, and we are a world-class, deeply technical team of ML researchers. Pluralis is unapologetically ideological. We believe AI, and the world, end up on a better path if we succeed in implementing the protocol for intelligence. If this resonates, please apply.
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.