Research Engineer

Job Summary

To support cutting-edge AI safety research, the full-time Research Engineer will design and implement experimental systems for evaluating misalignment and loss-of-control risks in frontier models, working remotely while collaborating closely with researchers.

Key responsibilities

• Design, implement, and run evaluations of misalignment and loss-of-control risks in frontier models
• Build realistic agent environments and tool integrations for studying behavior under increasing autonomy
• Develop infrastructure for long-horizon experiments and ensure experimental reliability and reproducibility

Required qualifications

• Strong Python and general software-engineering skills
• Experience working with language models, agentic systems, or model evaluations
• Ability to turn underspecified research questions into reliable experimental setups
• Strong engineering practices, particularly around reproducibility and data integrity
• Clear technical writing and communication skills