Researcher, Alignment

The role

You will design and implement experiments for alignment research. This involves developing alignment capabilities, designing evaluations for risks, and building tools to test model robustness.

What you will do

• Develop and evaluate alignment capabilities that are subjective, context-dependent, and hard to measure.
• Design evaluations to reliably measure risks and alignment with human intent and values.
• Build tools and evaluations to study and test model robustness in different situations.
• Design experiments to understand laws for how alignment scales.
• Design and evaluate new Human-AI-interaction paradigms and scalable oversight methods.
• Train model to be calibrated on correctness and risk.
• Designing novel approaches for using AI in alignment research

Required qualifications

• PhD or equivalent experience in research in computer science, computational science, data science, cognitive science, or similar fields.
• Strong engineering skills, particularly in designing and optimizing large-scale machine learning systems (e.g., PyTorch).
• Deep understanding of the science behind alignment algorithms and techniques.
• Can develop data visualization or data collection interfaces (e.g., TypeScript, Python).

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. They seek to safely deploy AI to the world through their products.