Research Scientist – Post-Training

🕒 October 14

⏰ Full Time

🟠 Senior

🔴 Lead

🧬 Research Scientist

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 October 14

Still open on Pluralis Research's site. Checked 2 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 returning updated weights to 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 from run to 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profiling before optimizing • Publications in RL post-training, asynchronous or distributed RL, or nearby fields, or unpublished work defensible in detail • Belief in Protocol Learning as a viable approach for collective, trustless, and sovereign AI • Professional-level English proficiency, written and spoken • Comfortable working across time zones • Experience training over slow networks or with decentralized or federated setups is a plus • Familiarity with vLLM or SGLang serving internals is a plus • Experience with reward modeling or verifiable-reward datasets is a plus • Experience with P2P networking and NAT traversal is a plus • Experience at proprietary, open-weight, and open-source AI labs is a plus

🏖️ Benefits

• Significant equity ownership in addition to a high base salary • Flexible work environment • Full visa sponsorship and relocation support to either Australia or the US for exceptional candidates • Opportunity to work on open research problems and write some of the first solutions

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

🕒 October 14

Praxis

11 - 50

🏥 Healthcare

💼 Consulting

📦 Logistics

Principal Scientist leading analytical development for Praxis, a clinical-stage biopharmaceutical company developing CNS therapies. Managing methods, GMP strategies, and external partners across the product lifecycle.

🕒 October 14

Thomson Reuters

10,000+ employees

💼 Consulting

⚖️ Legal

🛡️ Insurance

Lead Applied Scientist designing production search and retrieval systems for Thomson Reuters legal, tax, and accounting products. Driving ranking, semantic retrieval, evaluation, and AI strategy.

🕒 October 12

Telix Pharmaceuticals Limited

501 - 1000

🏥 Healthcare

💼 Consulting

🧬 Biotechnology

Principal Scientist leading biologics process development and CMC manufacturing activities at Telix Pharmaceuticals. Managing technology development, regulatory content, and external partner collaborations for precision oncology medicines.

🕒 October 11

Kled AI

11 - 50

🤖 Artificial Intelligence

🏪 Marketplace

🤝 B2B

Research Scientist building image, video, and document benchmarks for Kled’s opt-in human data network. Measuring data value for frontier AI models and informing data deals.

🕒 October 9

Praxis

11 - 50

🏥 Healthcare

💼 Consulting

📦 Logistics

Principal Scientist leading drug-substance process chemistry for Praxis, a clinical-stage CNS biopharmaceutical company. Driving development, manufacturing strategy, CRO/CDMO execution, and regulatory submissions.

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