Research Scientist – Post-Training

Pluralis Research

. Build the RL post-training stack end-to-end, including rollout ingestion, reward computation, policy updates, and returning updated weights to the network .

Posted 10/14/2026full-timeRemote • California • United States, AustraliaMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and executing RL post-training stacks, including rollout ingestion and policy updates, with a strong focus on asynchronous training and decentralized model delivery. Proficient in Python and PyTorch, with a solid understanding of reward modeling and communication-efficient updates.

Highest-signal resume keywords

RL Post-Training ExperiencePython ProgrammingPyTorch FrameworkAsynchronous Training LoopsReward Modeling

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

RLHFRLVRRollout GenerationWeight SynchronizationConcurrency HandlingProfiling and OptimizationPublications in RLDecentralized AI TrainingReward ComputationPolicy Updates

Soft Skills

Professional-Level English ProficiencyComfortable Working Across Time Zones

Tools & Technologies

VLLMSGLangP2P NetworkingNAT Traversal

Industry Keywords

Trustless AISovereign AIDistributed RLModel ImprovementPublic Artifact Delivery

Tech Stack

Tools & technologies

PythonPyTorch

About the role

Key responsibilities & impact

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

What you’ll need

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

Comp & perks

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