CHAI Research Fellowship: Center for Human-Compatible AI (CHAI)

This postdoctoral fellowship at the Center for Human-Compatible AI (CHAI) is designed to train researchers in advancing beneficial AI. Fellows will collaborate with CHAI faculty (Stuart Russell, Pieter Abbeel, Anca Dragan) and affiliates at Berkeley AI Research and other institutions. The research focuses on areas like reasoning, decision-making, learning, multi-agent systems, and the philosophical foundations of AI, utilizing tools such as probability and game theory.

Responsibilities
Pursue novel research projects in areas like intelligent agent architecture, lifelong learning, human-robot interaction, human preferences, and robust multi-agent cooperation.

Potentially lead collaborations, advise students, and teach courses.

Requirements
A PhD (or nearing completion) in computer science, statistics, mathematics, or theoretical economics.

High-quality published research.

An understanding of AI and statistical learning is advantageous, though prior work in AI control is not required.

The application requires a resume, a statement of interest, and two referees.