Job Posting

Title Postdoc Position in Expanding Machine Learning Beyond Social Prediction to Explanation and Intervention
Company Knowledge Lab, UChicago

The Knowledge Lab at the University of Chicago seeks to hire 1-2 outstanding candidates for a
postdoctoral research opportunity with support from DARPA to extend the limits of machine learning
from predicting social systems to explaining causal factors in those systems to intervening in them (see
recent press release here). This is in association with the “Ground Truth” program at DARPA. Other
teams will generate reasonable agent-based models of diverse social systems, and our task is to build
automated, analytical techniques that induce the "ground truth" or structure of the model and program
used to generate them. We will also predict future instances of these social systems, and propose desirable
and pragmatic interventions in them. Our team, the "Social MIND (Machine Inference for Novel
Discovery)”, is exploring approaches that use large-scale Bayesian inference, probabilistic programming,
deep learning neural networks, and approaches that link them together. We are recruiting for 1-2 postdoc
positions at the intersection of data science, machine learning, automated scientific discovery, and social
Postdoctoral candidates will design and conduct independent research, in close collaboration with
UChicago professor and Knowledge Lab Director, James Evans, along with Josh Tenenbaum,
computational cognitive scientist at MIT, and Michael Franklin, computer scientist and leader in systems
design at the University of Chicago. Candidates must have substantial computational and data science
background and hold a Ph.D. in Computer Science, Statistics, Applied Math, Physics, Sociology, Economics,
Psychology or another Social/Behavioral Science. Candidates should have a strong publishing record.
Regardless of degree, experience with social science theory and methods a strong plus. Comfort working
collaboratively with a research team is essential.
Specifically, successful candidates will be responsible for generating and automatically decoding agentmodels,
and applying these techniques to real social systems. Experience with some of the following will
be helpful: causal analysis, deep neural networks, Bayesian inference, probabilistic programming, machine
learning, and machine understanding. Candidates will be involved in both innovating new methods for
specific inference tasks, and assembling approaches into automated data analytic pipelines. The broader
project will also involve crowdsourcing alternative approaches, so experience with crowdsourcing and
intelligent model combination also a plus. Because we will be requesting social data from the agentmodeling
teams, understanding social science data gathering methods and familiarity with agent-based and
game theoretic models will be very helpful. A working knowledge of Python, as well as experience with
relevant libraries (e.g., scikit-learn, pandas, tf, keras, pytorch, pymc, igraph, etc.) is required. Familiarity
with bash, ssh, git, databases (e.g. mysql) and AWS is expected. Positions could begin anytime within the
coming year, and as early as September 2018. Competitive salary & benefits.
To apply, please send CV, cover letter and names for letters from at least two references to Candice

Location Searle Chemistry Laboratory
Deadline 27 June 2019

Candice Lewis

Job Type Full Time
Attachment Postdoc_DARPA.pdf