Research Scientist (Philosophy)

Resolution•Berkeley, CA

3d•Onsite

About The Position

Resolution is conducting research on artificial superintelligence (ASI) alignment, aiming to ensure aligned outcomes as ASI development progresses. The philosophy team at Resolution focuses on the conceptual and normative questions that arise in AI alignment research. This includes examining concepts like honesty and harm, understanding character and moral competence in AI, evaluating different moral theories for AI guidance, and assessing the risks of automating conceptual reasoning. The team seeks to advance alignment by rigorously examining these philosophical questions and conducting empirical tests where appropriate. The role involves contributing to or leading original research projects, connecting philosophical analysis to empirical hypotheses and AI development practices, and collaborating with machine learning researchers. The team is new, and new hires will significantly shape its direction.

Requirements

Hold a PhD in a relevant field, such as philosophy, cognitive science, psychology, mathematics, or machine learning, or have a record of rigorous research experience.
Demonstrate motivation to work on AI alignment, including through previous publications in the field, relevant experiences, or a clear explanation of why you are pivoting your research focus to alignment.
Ability to identify important questions in areas where the problems, concepts, or success criteria remain unclear.
Interest in connecting philosophical analysis with empirical research.
Ability to communicate clearly and collaborate productively with researchers from different disciplinary backgrounds.

Nice To Haves

Research experience in AI safety, AI alignment, or other domains relevant to making AI futures go well.
The ability to design, run, or help develop experiments.
Previous experience working in interdisciplinary research teams.
The interest and capacity to translate conceptual questions into hypotheses, interventions, or evaluation criteria.
Relevant expertise in areas such as epistemology, philosophy of science, philosophy of language, philosophy of mind, action theory, moral psychology, or ethics.

Responsibilities

Lead or contribute to original research projects in philosophy and AI alignment.
Identify important but underspecified problems and turn them into projects.
Connect philosophical analysis to empirical hypotheses, experimental designs, training approaches, or evaluation methods.
Collaborate closely with researchers from machine learning and other relevant disciplines.
Communicate research clearly through papers, internal reports, presentations, and external engagement.
Contribute to the intellectual culture and development of the philosophy team and Resolution.
Define and lead broad or ambiguous areas of research (depending on seniority).
Help set the team’s research agenda and strategic priorities (depending on seniority).
Initiate and lead collaborations across Resolution and with external researchers (depending on seniority).
Supervise, mentor, or manage more junior researchers (depending on seniority).
Represent the philosophy team in organization-wide research planning (depending on seniority).