Jobs at Polymath
Long-horizon RL
About Polymath
Long-horizon RL
[ Open roles ]
- Member of Technical Staff - ResearchNot specified
Polymath is hiring a Founding Member of Technical Staff - Research to advance long-horizon agent capabilities using reinforcement learning. The role involves core research in agent evaluation, post-training, and environment design, focusing on identifying and improving model failures. Responsibilities include building benchmarks, creating environments, writing production code, and running experiments.
- Member of Technical Staff - EngineeringNot specified
Founding Member of Technical Staff - Engineering at Polymath. This role focuses on building the infrastructure and systems for environment simulation products, enabling the training and evaluation of autonomous AI agents. The position involves working on the technical foundation for complex, realistic environments and requires a broad range of engineering skills.
- Strategic Projects LeadNot specified
As a Founding Strategic Projects Lead at Polymath, you will work on high-leverage initiatives across partnerships, data, and new market expansion. This cross-functional role involves tackling open-ended problems and shaping the company's trajectory by working closely with founders on critical strategic efforts. Key responsibilities include creating best practices for organizing domain experts, scaling the expert contributor network, and leading complex data projects from inception to completion.
- Software EngineerRemote
Software Engineers at Polymath build simulation environments, tasks, and verifiers to challenge frontier models and improve autonomous agents. This role involves creating realistic training and evaluation grounds, designing complex tasks requiring long-horizon reasoning, and developing robust verifiers for agent performance measurement.