*Summary:* Stuart Russell's Center for Human Compatible AI at UC Berkeley has postdoc openings <http://humancompatible.ai/> with a flexible start date; apply ASAP (details below). ***** The Centre for Human-Compatible Artificial Intelligence (CHCAI) at Berkeley has openings for one or more postdoctoral researchers. Successful candidates will work with the CHCAI Director, Stuart Russell, or with one of the Berkeley co-Principal Investigators, Pieter Abbeel, Anca Dragan, and Tom Griffiths. There will also be opportunities to collaborate with CHCAI investigators at Cornell (Bart Selman, Joe Halpern) and Michigan (Michael Wellman, Satinder Singh), as well as with groups at Cambridge, Oxford, and Imperial College through the Leverhulme Centre for the Future of Intelligence.
CHCAI’s goal is to ensure that as the capabilities of AI systems increase, their impact remains provably beneficial for humans. This requires a significant reorientation of the general thrust of AI research, which up to now has been largely concerned with designing systems that optimize exogenously specified objectives. Given the broad and open-ended mandate of the Center, the post holder will have considerable freedom to pursue novel research projects within CHCAI’s areas of interest, either individually or working with PhD students and undergraduate researchers. Early examples of CHCAI’s work include a recent paper on cooperative inverse reinforcement learning <https://arxiv.org/abs/1606.03137> (to appear in NIPS 16). Related work includes some results from FHI’s collaboration with Google DeepMind <https://intelligence.org/files/Interruptibility.pdf> and the descriptions of research problems by Google Brain <https://arxiv.org/abs/1606.06565> and by the Machine Intelligence Research Institute <https://intelligence.org/files/TechnicalAgenda.pdf> Candidates need not have done previous work on the AI control problem but must have (or be about to obtain) a PhD in a relevant technical discipline (computer science, statistics, mathematics, or theoretical economics) and a record of high-quality published research. A solid understanding of current methods in AI and statistical learning would be an advantage. If you fit this description and would like to arrange a conversation with someone at the Center about what it would be like to work here, email Andrew Critch ( [email protected]) with your CV attached. If you choose to apply, full applications should be mailed to [email protected] and should include a CV, the names and contact details of three academic referees, and a one-page statement of interest describing in general terms the kind of research you would like to undertake.
_______________________________________________ uai mailing list [email protected] https://secure.engr.oregonstate.edu/mailman/listinfo/uai
