Empirical Researcher

At Redwood Research, we strive to ensure the safe development of artificial intelligence through rigorous technical research, thoughtful analysis, and strategic advising.

As an empirical researcher, you will design and run experiments on frontier language models to assess AI risks and test the safety measures meant to address them.

• Basic familiarity with AI safety and threat models
• Basic familiarity with running modern frontier LLM experiments

• Deep context on AI safety
• Strong writing skills
• Well-read on the state of risk assessments and risk reports out of AI companies
• Familiarity with AI evaluation methodologies, in particular for loss-of-control threat models
• Knowledge of computer security
• Deep and broad knowledge of ML
• For senior roles: management experience, experience publishing papers in top conferences, and experience leading big research projects

• Read all the risk reports, such as this recent one by Redwood and METR
• Read system cards for model releases
• Read most of the Redwood blog
• Go through our AI Futurism reading list
• Read Building Secure and Reliable Systems

Our application process includes work tests and interviews. In most cases we will not offer a full-time position immediately, but instead offer a 4‑month work trial.