The entry of Artificial Intelligence into prominent social and economic environments has brought to the fore concerns about the ethical nature of such agents and tools. Though it is well-known that methods based in utilitarian calculus often fail to account for moral considerations, few alternatives have been adopted in the field of AI. My work advocates for a new approach toward the interaction between AI methods and the social that centers principles of distributive justice. As AI increasingly drives consequential social decision-making, we must consider not only what can be done but what ought to be done. Grappling with the inherently normative nature of these problems requires an orientation towards AI that is able to conceptualize justice beyond utility.

The persistence of racial inequality in the U.S. labor market against a general backdrop of formal equality of opportunity is a troubling phenomenon that has significant ramifications on the design of hiring policies. In this paper, we show that current group disparate outcomes may be immovable even when hiring decisions are bound by an input-output notion of "individual fairness." Instead, we construct a dynamic reputational model of the labor market that illustrates the reinforcing nature of asymmetric outcomes resulting from groups» divergent accesses to resources and as a result, investment choices. To address these disparities, we adopt a dual labor market composed of a Temporary Labor Market (TLM), in which firms» hiring strategies are constrained to ensure statistical parity of workers granted entry into the pipeline, and a Permanent Labor Market (PLM), in which firms hire top performers as desired. Individual worker reputations produce externalities for their group; the corresponding feedback loop raises the collective reputation of the initially disadvantaged group via a TLM fairness intervention that need not be permanent. We show that such a restriction on hiring practices induces an equilibrium that, under particular market conditions, Pareto-dominates those arising from strategies that statistically discriminate or employ a "group-blind" criterion. The enduring nature of equilibria that are both inequitable and Pareto suboptimal suggests that fairness interventions beyond procedural checks of hiring decisions will be of critical importance in a world where machines play a greater role in the employment process.