Research Scientist - Post-Training

OpenKrill; United States; A distancia; USD 180.000 - 280.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity-heavy package

Remote-first culture

Visa sponsorship and relocation to US

Relocation support to Australia

Descripción de la vacante

Pluralis Research is hiring a specialist to advance Protocol Learning by building RL post-training stacks that run across consumer GPUs and the public internet. You will adapt RL algorithms to asynchronous, high-latency, decentralized settings, and ship first post-trained models.

The role demands strong Python/PyTorch engineering, distributed systems expertise, and a passion for protocol learning. You will work with a global team to push the boundaries of decentralized AI, delivering robust

Formación

• RL post-training on large language models and systems-level work.
• Experience with rollout generation and async training loops.
• Publications in RL/post-training or related fields are a plus.
• Ability to work across time zones and with remote teams.

Responsabilidades

• Build end-to-end RL post-training stack including rollout ingestion and policy updates.
• Develop asynchronous, high-latency training pipelines and weight synchronization.
• Evaluate and release first decentralized post-trained models.

Conocimientos

Python

PyTorch

Distributed systems

RL post-training

English proficiency

Herramientas

vLLM

SGLang

Git

Descripción del empleo

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 https://arxiv.org/abs/2607.13332). 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 https://pluralis.ai/blog/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.
• 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.

We are backed by Union Square Ventures https://www.usv.com/ 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.