Software Engineer

The role

Software Engineers will build simulation environments, tasks, and verifiers to challenge frontier models. You will create training and evaluation grounds to measure and improve autonomous agents.

What you will do

• Build diverse, high-fidelity environments that test agents in realistic settings
• Design complex tasks that require long-horizon reasoning and tool use
• Develop robust verifiers that reliably measure agent performance
• Improve infrastructure and tooling to run, debug, and improve environments
• Work closely with the research team to identify failure modes and turn them into new tasks and benchmarks

Required qualifications

• Strong engineering fundamentals
• Enjoy building from first principles and solving open-ended technical problems
• High agency and a strong bias toward shipping
• High quality bar and care about building robust systems

About the company

Polymath is an applied research lab focused on advancing long-horizon agent capabilities through reinforcement learning. They design and scale simulation environments where agents learn to operate safely and autonomously.