Research Engineer – Post-Training

🕒 August 31

⏰ Full Time

🟠 Senior

🔴 Lead

📚 Research Engineer

Where this job comes from

Posted on Pluralis Research's careers page ↗Pluralis Research's careers page, not through a job board

First seen by Remote Rocketship August 31

Still open on Pluralis Research's site. Checked 3 hours ago.

Apply Now
Logo of Pluralis Research

Pluralis Research

1 - 10 employees

🤖 Artificial Intelligence

🌐 Web 3

Artificial Intelligence • Web 3

Pluralis Research is a foundational AI research lab focused on Protocol Learning — decentralized, multi‑participant training of foundation models where no single participant holds a full copy of the model. The group develops methods to enable communication‑efficient model and pipeline parallelism, unextractable collaborative models, and high‑compression context parallelism so community‑trained, community‑owned frontier models can scale over low‑bandwidth, internet‑connected devices. Their work targets practical systems and algorithms that make decentralized training competitive with centralized training while enabling new ownership and economic models.

📋 Description

• Build the RL post-training stack end-to-end, including rollout ingestion, reward computation, policy updates, and distributing updated weights across the network • Set the direction for the post-training stack and execute its development • Adapt RL algorithms to asynchronous, high-latency, partially trusted generation • Address staleness tolerance, off-policy corrections, and communication-efficient policy updates • Build evaluations demonstrating model improvement • Deliver the first decentralized post-trained model release as a public artifact

🎯 Requirements

• Hands-on experience running RL post-training on large language models, including RLHF, RLVR, or reasoning-focused RL • Experience with rollout generation, asynchronous training loops, and weight synchronization • Production-quality Python and PyTorch skills • Experience with concurrency, failure handling, and profiling before optimizing • Publications in RL post-training, asynchronous or distributed RL, or nearby fields, or unpublished work that can be defended in detail • Belief in Protocol Learning as a viable path for collective, trustless, and sovereign AI • Professional-level English proficiency, written and spoken • Comfort working across timezones • Nice to have: experience training over slow networks or with decentralized/federated setups • Nice to have: familiarity with vLLM or SGLang serving internals • Nice to have: experience with reward modeling or verifiable-reward datasets • Nice to have: experience with P2P networking and NAT traversal • Nice to have: experience at proprietary, open-weight, and open-source AI labs

🏖️ Benefits

• Significant equity ownership for key technical contributors in addition to a high base salary • Flexible work environment with team members distributed globally • Optional full visa sponsorship and relocation support to either Australia or the US

Apply Now

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

🕒 August 19

LiveKit

11 - 50

🔌 API

🤖 Artificial Intelligence

📡 Telecommunications

Research Engineer building reinforcement-learning models for LiveKit’s voice AI infrastructure. Developing training data, evaluations, and production models for voice, SMS, and chat agents.

🇺🇸 United States – Remote

💵 $135k - $300k / year

💰 Venture Round on 2022-09

⏰ Full Time

🟡 Mid-level

🟠 Senior

📚 Research Engineer

🕒 August 7

Built

201 - 500

🏗️ Construction

💼 Consulting

📦 Logistics

Staff Innovation Engineer building AI-powered marketplace services for Built, an AI platform for construction and real estate finance. Developing microservices, customer-tested products, and LLM workflows.

🕒 August 7

Sony Interactive Entertainment

10,000+ employees

🎮 Gaming

🔧 Hardware

📡 Telecommunications

Senior Security Research Engineer advancing threat exposure management for PlayStation. Leading vulnerability research, validation, prioritization, and remediation across Sony’s technology environments.

🕒 July 28

Surge AI

51 - 200

🤖 Artificial Intelligence

🔌 API

☁️ SaaS

Research Engineer at Surge working at the intersection of software engineering and AI training data. Owning coding data projects to teach frontier models how to code.

🕒 July 28

Sequen

11 - 50

☁️ SaaS

🤖 Artificial Intelligence

🤝 B2B

Staff+ Forward Deployed Research Engineer at Sequen developing production-grade systems for AI-driven ranking and recommendations. Working at the intersection of AI research and customized deployment inside enterprise environments.

Developed by Lior Neu-ner. I'd love to hear your feedback — Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok