Machine Learning Engineer, Evals
Frontier labonsite
At a glance
Highlights
- Ship evaluation infrastructure researchers depend on from day one.
- Design benchmarks and LLM-as-judge systems for agent capabilities.
- Own weekly regression suites and failure analysis with recommendations.
Ideal candidate
High-ownership builder who thrives on small teams and cares about rigorous measurement of AI agents. You love digging into failures and turning insights into trusted infrastructure.
Lab profile
About Nous Research
Decentralized AI lab building open Hermes models and personal AI agents.
What they build
- Hermes Agent
- Nous Portal
- Hermes Enterprise
Known for
- Open-source Hermes models
- Personalized self-improving agents
- Global community-driven development
Key facts
- Founded in 2023
- New York office
- $50M Series A led by Paradigm
First seen · Last seen