Our Team

We’re Hiring!

Find out more about the opportunities to join our growing team here.

Staff

Luke Muehlhauser

Luke Muehlhauser
Executive Director

Luke Muehlhauser (email) is MIRI’s Executive Director. Since joining MIRI he has organized many research workshops, grown collaborations with Oxford University, Cambridge University, and MIT, and published articles in Communications of the ACM, Slate, Quartz, and other venues. Previously he was a team leader for deploying mission-critical enterprise-wide IT solutions in Los Angeles.

Eliezer Yudkowsky

Eliezer Yudkowsky
Senior Research Fellow

Eliezer Yudkowsky (email) is internationally recognized by the academic community for his role in developing the foundations of Friendly AI research. His ideas and technical research have become a focal point for research workshops held around the world and attended by researchers from Stanford, Harvard, Cambridge, MIT, UC Berkeley, Princeton, Google, and other leading institutions. He is also a promoter of “applied rationality” whose writings on psychology and philosophy of science have made the latest research in these fields accessible to thousands of teens and adults.

Benja Fallenstein

Benja Fallenstein
Research Fellow

Benja Fallenstein (email) does mathematical research on Friendly AI, including problems of self-reference and issues in decision and game theory when an AI reasons about future versions of itself or about other, similarly powerful agents in its environment; models of logical uncertainty, i.e., uncertainty about what mathematical statements are true; models of anthropic reasoning; and the specification of safe AI goals. Benja is also interested in formal verification and in programming languages with integrated proof checkers. Benja holds a Bachelors in Mathematics from University of Vienna.

Nate Soares

Nate Soares
Research Fellow

Nate Soares (email) is broadly interested in Friendly AI research, specifically reflective trust, decision theory, game theory, and goal specification. He has undergraduate degrees in computer science and economics, and often studies mathematical logic, probability theory, category theory, and type theory. Nate previously worked for Google.

Malo Bourgon

Malo Bourgon
Program Management Analyst

Malo Bourgon (email) improves the efficiency and effectiveness of all aspects of MIRI, from research and outreach programs to operations and fundraising efforts. He also manages MIRI’s internship and volunteer programs, assists with capacity building, and generally helps make things happen. Malo holds a Masters in Engineering from the University of Guelph.

Alex Vermeer

Alex Vermeer
Program Management Analyst

Alex Vermeer (email) improves MIRI’s operations and output by measuring useful data, identifying inefficiencies, and improving processes. He also handles MIRI’s web development and manages MIRI’s document production team. Alex holds an Engineering degree from the University of Guelph.

Katja Grace

Katja Grace
Research Assistant

Katja Grace’s (email) research at MIRI focuses on social and historical questions related to artificial intelligence outcomes. She recently wrote Algorithmic Progress in Six Domains. She is sometimes a PhD student in Logic, Computation & Methodology at Carnegie Mellon University. She writes the blog Meteuphoric.

Rob Bensinger

Rob Bensinger
Research Assistant

Rob Bensinger (email) focuses on attempts to relate human categories and preferences to physical phenomena. He has a BA in Philosophy and a certificate in History and Philosophy of Science, both from Indiana University. His research interests include consciousness studies, value theory, and the psychology of moral, religious, and broadly theory-dependent reasoning.

2014 Research Advisors

Nick Bostrom

Nick Bostrom

PROFESSOR
University of Oxford
DIRECTOR
Future of Humanity Institute

Max Tegmark

Max Tegmark

PROFESSOR
Massachusetts Institute of Technology
SCIENTIFIC DIRECTOR
Foundational Questions Institute

Gary Drescher

Gary Drescher

PhD
Massachusetts Institute of Technology
AUTHOR
Made-Up Minds

Robin Hanson

Robin Hanson

PROFESSOR
George Mason University
AUTHOR
Economic Growth Given Machine Intelligence

Steve Omohundro

Steve Omohundro

PhD
UC Berkeley
AUTHOR
Rational Artificial Intelligence for the Greater Good

Moshe Looks

Moshe Looks

PhD
Washington University
SCIENTIST
Google Research

Roman Yampolskiy

Roman Yampolskiy

PROFESSOR
University of Louisville
AUTHOR
Artificial Intelligence Safety Engineering

 

2014 General Advisors

Peter Thiel

Peter Thiel

Co-founder
PayPal

Christine Peterson

Christine Peterson

Co-founder
Foresight Institute

Liron Shapira

Liron Shapira

Co-founder & CTO
Quixey

Research Associates

Alex Altair

Alex Altair
Research Associate

Alex Altair (email) researches trusted reasoning formalisms for autonomous systems. He published “A Comparison of Decision Algorithms on Newcomblike Problems” and co-authored the “Intuitive Explanation of Solomonoff Induction.” He graduated from the Maine School of Science and Mathematics, and studied physics and mathematics at university.

Mihaly Barasz

Mihaly Barasz
Research Associate

Mihaly Barasz (email) is interested in functional languages and type theory and their application in formal proof systems. He cares deeply about reducing existential risks. He has an MSc summa cum laude in Mathematics from Eotvos Lorand University, Budapest and currently works at Google.

Paul Christiano

Paul Christiano
Research Associate

Paul Christiano (email) recently finished an undergraduate degree in mathematics at MIT and is now a graduate student at UC Berkeley. His research on algorithms and cryptography has been presented at top conferences in theoretical computer science. In 2008 he was one of six students to represent the U.S. at the International Mathematics Olympiad. He is also the lead author of MIRI research paper “Definability of Truth in Probabilistic Logic.”

Daniel Dewey

Daniel Dewey
Research Associate

Daniel Dewey (email) works on the theory of artificial general intelligence. His current research focuses on optimality notions for physically implemented AGI, motivated self-deception, and goal safety. Daniel has a BSc in Computer Science from Carnegie Mellon University. You can find more of his work at danieldewey.net.

Marcello Herreshoff

Marcello Herreshoff
Research Associate

Marcello Herreshoff (email) has worked with MIRI on the math of Friendly AI from time to time since 2007. In high school, he was a two time USACO finalist and he published a novel combinatorics result, which he presented at the Twelfth International Conference on Fibonacci Numbers and Their Applications. He holds a BA in Math from Stanford University. At Stanford he was awarded two honorable mentions on the Putnam mathematics competition, and submitted his honors thesis for publication in the Logic Journal of the IGPL. His research interests include mathematical logic and its use in formalizing coherent goal systems.

Bill Hibbard

Bill Hibbard
Research Associate

Bill Hibbard (email) is an Emeritus Senior Scientist at the University of Wisconsin-Madison Space Science and Engineering Center, currently working on issues of AI safety and unintended behaviors. He has a BA in Mathematics and MS and PhD in Computer Sciences, all from the University of Wisconsin-Madison. He is the author of Super-Intelligent Machines, “Avoiding Unintended AI Behaviors,” and “Decision Support for Safe AI Design.”

Patrick LaVictoire

Patrick LaVictoire
Research Associate

Patrick LaVictoire (email) is interested in the mathematics of decision theory: when different algorithms can read one anothers’ source code before choosing actions, there are some Gödelian strategies that provably do better than causal decision theory. Patrick has an AB in Mathematics from the University of Chicago and a PhD in Mathematics from the University of California at Berkeley, and is currently a Van Vleck Visiting Assistant Professor of Mathematics at the University of Wisconsin-Madison.

Kaj Sotala

Kaj Sotala
Research Associate

Kaj Sotala (email) is interested in the strategic questions related to AI risk. He has authored and co-authored several papers on the topic, including “Responses to Catastrophic AGI Risk: A Survey,” “How We’re Predicting AI — or Failing To,” “Advantages of Artificial Intelligences, Uploads, and Digital Minds,” and “Coalescing Minds: Brain Uploading-Related Group Mind Scenarios.” Kaj holds a BA in Cognitive Science from the University of Helsinki, where he is currently studying Computer Science.

Nisan Stiennon

Nisan Stiennon
Research Associate

Nisan Stiennon (email) is interested in formal decision theory—the mathematical study of the way abstract agents behave, and what this implies about the values and behavior of humans. Nisan has a PhD in mathematics from Stanford and works with the Center For Applied Rationality.

Board

Edwin Evans<br /><small>CHAIR</small>

Edwin Evans
CHAIR

Vice President of Engineering
Proximiant

Kevin Fischer<br /><small>DIRECTOR</small>

Kevin Fischer
DIRECTOR

Chief Executive Officer
GetCBD

Tomer Kagan<br /><small>DIRECTOR</small>

Tomer Kagan
DIRECTOR

Chief Executive Officer
Quixey

Michael Vassar<br /><small>DIRECTOR</small>

Michael Vassar
DIRECTOR

Chief Science Officer
Metamed

Eliezer Yudkowsky<br /><small>DIRECTOR</small>

Eliezer Yudkowsky
DIRECTOR

Senior Research Fellow
Machine Intelligence Research Institute

Interested in joining our team?