SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Pluralis Research is building Protocol Learning: a system for training and serving large language models in a fully decentralized way on consumer-grade devices connected via the internet. The company has already demonstrated feasibility with Agora, a permissionless run that pretrained an 8B model from scratch on consumer GPUs distributed across the internet, with no single participant ever holding the full weights.
As Research Scientist - Post-Training, you will own the end-to-end post-training stack that makes decentralized models useful for agentic applications. This is a greenfield research and engineering challenge: standard post-training assumes datacenter infrastructure with synchronous rollouts, fast interconnects, and trusted workers. Pluralis has none of that. The post-training system must run on consumer GPUs and Macs spread across the public internet, training a model whose weights no single participant holds, with rollouts arriving from a geo-distributed inference pipeline at high latencies.
Your primary responsibilities:
- Build the post-training stack end-to-end: rollout ingestion from the geo-distributed inference pipeline, reward computation, policy updates, and weight distribution back to the network. You set direction and make things happen.
- Invent novel algorithms: adapt standard RL recipes (which assume on-policy rollouts from fast, trusted hardware) to asynchronous, high-latency, partially trusted generation. This includes staleness tolerance, off-policy corrections, and communication-efficient policy updates.
- Ship first post-trained models: build evaluation frameworks that demonstrate model improvement and take the first decentralized post-trained release from run to public artifact.
The team is distributed globally with main hubs in Australia and North America. You will work across timezones with a world-class, deeply technical team of ML researchers backed by Union Square Ventures and other tier-1 investors. The company offers visa sponsorship and relocation support to Australia or the US if desired.
REQUIREMENTS:
- Hands-on experience running RL post-training on large language models (RLHF, RLVR, or reasoning-focused RL), with direct involvement in systems layer work: rollout generation, async training loops, weight synchronization. Not launching jobs on someone else's stack.
- Strong production-level Python and PyTorch engineering: concurrency, failure handling, profiling and optimization.
- Research ability demonstrated through publications in RL post-training, asynchronous or distributed RL, or adjacent fields. Unpublished work you can defend in detail is also valued.
- Mission alignment: belief that Protocol Learning is a viable third path for collective, trustless, and sovereign AI.
- Professional-level English proficiency (written and spoken).
NICE TO HAVE:
- Experience training over slow networks or with decentralized/federated setups.
- Familiarity with serving-engine internals (vLLM, SGLang).
- Experience with reward modeling or building verifiable-reward datasets.
- Experience with P2P networking and NAT traversal.
- Background at proprietary, open-weight, or open-source AI labs.
