Job 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• Publications in RL post-training, asynchronous or distributed RL, or nearby fields, or unpublished work defensible in detail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