Research Engineer - Post-Training RL & Distributed Learning

About Templar AI

Templar is redefining how large language models are trained. The team enables permissionless pretraining — allowing collaborators across diverse computational environments to jointly train LLMs without centralized coordination. No single entity controls the process. Anyone can contribute compute, and the system is designed to handle it.

 Templar's latest research, "Incentivizing Permissionless Distributed Learning of LLMs," introduces Gauntlet — an on-chain incentive system that powered a fully decentralized 1.2B parameter LLM training run. The work represents a meaningful step toward community-driven AI development at scale, and the team is now pushing further into post-training and the infrastructure required to make distributed learning work across the full training stack.

 

The Opportunity

Templar is looking for a Research Engineer to work across the post-training and pre-training stacks in a decentralized, community-driven training environment. You will contribute to state-of-the-art post-training pipelines running on real-world decentralized infrastructure, implement and evaluate ideas relevant to scaling large-scale post-training, and help push the frontier of what distributed LLM training can do.

 This is a research engineering role — you will be both building systems and contributing to the ideas that shape them. The environment is fast-moving, highly technical, and fully remote.

 

What You'll Do

• •      Contribute to the development of decentralized training of large language models
• •      Work across the post-training and pre-training stacks
• •      Implement and evaluate ideas relevant to scaling large-scale post-training on decentralized infrastructure
• •      Contribute to training runs and writing technical reports

 

You Should Have

• •      Strong programming skills with experience training models across multiple devices
• •      Solid foundations in machine learning
• •      Clear written and verbal communication skills
• •      Ability to work independently in a fast-moving, remote environment

 

Nice to Have

• •      Experience with LLM RL post-training or large-scale pre-training
• •      Publications or research experience in relevant areas such as distributed learning, reinforcement learning from human feedback, or scalable training infrastructure