About Paramerge
Stephen Lieberman
Responsible AI for the Real World
Stephen Lieberman helps organizations build the governance necessary for AI safety to survive contact with operational reality. All client work is confidential.
Most organizations deploying AI at scale already have safety policies. What they lack is leadership that can hold the line between those policies and what actually happens when capable systems meet real institutional pressure. That is the work I do: identifying where alignment breaks down before it breaks down, and building the technical and organizational conditions that make safety durable.
Available for fractional, remote, and in-house executive roles through Paramerge.
Stephen Lieberman
Track Record
Career Proof Points
20+
20+ years leading technical and operational teams
$100B+
Senior leadership on DoD/VA programs in $100B+ environments
$9.8M+
$9.8M+ in fully funded federal proposals · 100% funding success rate
20+
20+ peer-reviewed publications, book chapters, and conference papers
Selected organizations
Organizations where Stephen Lieberman has held roles, or whose programs he has led. This is career history, not a client list. All client work is confidential.
U.S. Department of Veterans Affairs
U.S. Department of Defense
U.S. Department of State
Federal Emergency Management Agency
Naval Postgraduate School
Defense Manpower Data Center
About
Stephen Lieberman
I lead AI safety and alignment work for organizations where capable AI is moving beyond what standard governance was built to handle. With more than 20 years leading technical and operational teams in mission-critical environments, I bring the institutional discipline and operational judgment that high-stakes AI governance demands.
The core argument: capable AI cannot be governed as if it were ordinary software. As systems scale, they move beyond what traditional analytic methods can model, producing emergent capabilities, emergent risks, and interaction effects with human systems that no evaluation framework fully captures. Closing that gap is a leadership problem before it is a technical one.
Through Paramerge, I work with organizations navigating the transition from controlled research conditions to real-world deployment at scale.
Mission-Critical Technical and Operational Leadership
More than 20 years leading technical and operational teams across government, defense, academia, nonprofit, and industry. Senior leadership on Department of Defense and Veterans Affairs programs within funding environments exceeding $100 billion ⓘ, spanning enterprise architecture, decision-support systems, security and compliance, electronic health records, cloud systems, and data strategy. Led programs with multimillion-dollar budgets and worked directly with senior leaders across defense, government, and institutional settings.
International Defense and Security Systems
At the Naval Postgraduate School, served as a DoD civilian program leader and Principal Investigator responsible for programs in defense technology, modeling and simulation, collaboration platforms, and decision-support systems, with more than $9.8 million ⓘ in fully funded federal proposals across six programs. Every proposal was funded at the amount requested. Among them, founded and led GlobalECCO, the Combating Terrorism Fellowship Program's international education and collaboration network, its serious games and collaboration systems grounded in simulation science coupled with real-world data and in silico testing. Work included counterterrorism, counterinsurgency, peacekeeping operations, and international collaboration across more than 100 countries. Recognized directly by the Assistant Secretary of Defense:
“Steve, you and your team have performed superbly. Your collective skills, resourcefulness, and creativity have created a ground-breaking tool that will benefit the U.S. government and our allies.”
Michael G. Vickers
Undersecretary of Defense for Intelligence, U.S. Department of Defense
Research in Complex Adaptive Systems
The research foundation of this work is an in-silico simulation framework built to model the Complex Adaptive Social System (CASS): whole societies, organizations, and markets treated as populations of coupled, adaptive agents. The framework is a federally validated simulation platform under the US Department of Defense Verification, Validation, and Accreditation (VV&A) process, built and published over nearly two decades. Originally developed at the Naval Postgraduate School for counterterrorism, peacekeeping, and international conflict environments, it has since been applied to organizational behavior, social policy, and human-machine interaction. It models the emergence of beliefs, values, and interests across whole societies at scale, applying network science, discrete event simulation, and behavioral survey data to forecast group-level dynamics in high-consequence environments.
Published work spans agent-based modeling methodology, social simulation validation, cognitive modeling from behavioral data, and violent extremist network dynamics. More than 20 peer-reviewed publications, book chapters, and conference papers, with an H-index of 7, more than 100 citations, and 8 highly influential papers indexed on Semantic Scholar.
Selected publications
Lieberman, S. (2012). Extensible software for whole of society modeling: framework and preliminary results. Simulation, 88(5), 557-564.
Lieberman, S. and Alt, J. (2010). Developing Social Networks for Artificial Societies from Survey Data. In Advances in Social Computing, Lecture Notes in Computer Science, Vol. 6007. Springer.
Alt, J. and Lieberman, S. (2010). Developing Cognitive Models for Social Simulations from Survey Data. In Advances in Social Computing, Lecture Notes in Computer Science, Vol. 6007. Springer.
Alt, J., Lieberman, S., and AlRowaei, A. (2010). Exploring the Implications of Time in Discrete Event Social Simulations. AAAI Spring Symposium Proceedings.
Applied Complexity in Live Equity Derivatives Markets
From 2015 to 2022, the CASS framework was extended into live US equity index derivatives markets as a rigorous, high-stakes validation of the methodology. Over seven years, agent-based simulation of coupled autonomous execution systems and human traders was applied to identify and operationalize the emergent cascading failure patterns those coupled systems produce under volatility stress. Significant in-silico testing preceded any live market participation, and simulation and live operation then ran together, applying the same pre-deployment validation standard that now grounds the AI safety governance work.
The operation was formally structured, with institutional-grade exchange access, multi-platform infrastructure across futures and options on ES and NQ contracts, and legal and tax architecture appropriate to the complexity of the instruments. The results validated the core thesis: that complex adaptive systems producing emergent behavior under stress are modelable in advance, governable through disciplined simulation, and consequentially different from what static evaluation frameworks can detect. During this period, formal participation in sessions convened by the CFTC, SEC, CME, and CBOT on the development of regulatory frameworks for cryptocurrency futures and derivatives contributed practitioner perspective at the formative stage of that policy development.
The intellectual through-line to AI safety governance is direct. Emergent behavior in live financial markets and emergent misalignment in AI systems at scale share the same underlying structure: nonlinear dynamics in human-automated systems that static testing cannot anticipate, that manifest only at scale and under stress, and that carry asymmetric consequences when governance fails. This research program is ongoing. Partnership with organizations seeking to extend this work into AI-relevant domains is actively welcomed.
AI Governance at the Intersection of Technology and Human Systems
The most significant gaps in real-world AI safety governance are not purely technical. They are organizational, institutional, and deeply human. Doctoral research at USC's Suzanne Dworak-Peck School of Social Work centers on governance architecture for AI systems deployed in professional and high-stakes institutional contexts. This builds on a research lineage running from graduate work on network-theoretic organizational resilience at the University of Connecticut, through doctoral training in computational modeling and simulation at the Naval Postgraduate School, to current work on the governance conditions that determine whether AI safety frameworks hold under real institutional pressure.
The capstone examines LLM governance in professional practice environments, arguing that the decisive barrier to safe AI integration is a governance architecture problem rather than a technical one, grounded in antifragile systems theory, community-based participatory design, and the organizational conditions that determine whether safety holds under real institutional pressure.
Approach draws on sociotechnical systems theory, organizational behavior, industrial psychology, human-centered design, and macro social work: disciplines that illuminate how people actually act inside institutions and how to intervene at the level of structural conditions rather than surface behaviors. That is precisely the level at which real-world AI governance must operate.
The Name
Why Paramerge
Paramerge is named for parameter emergence: the appearance of qualitatively new system-level behavior out of the interactions among a sufficiently large and complex set of parameters.
The operative word is interaction, not quantity. Parameters take part in distributed representations and non-linear relationships with one another. At sufficient scale those relationships produce higher-order structure and dynamics, and that structure produces behavior which is not readily attributable to any individual parameter. Nothing in the system holds a capability the way a file holds a value. The capability is in the configuration.
The pattern is familiar from other complex systems. No single neuron contains a thought. No individual molecule is wet, though water is. No one ant carries the colony’s foraging strategy, yet the colony has one. In each case the property belongs to the interactions rather than to any part, and it appears only once there are enough parts, richly enough connected, for those interactions to constitute a system in their own right.
parameter emergence
Not more parameters — what enough of them, interacting, become
Parameter scaling and parameter emergence are different claims. Scaling adds parameters. Parameter emergence is what those parameters begin to do to one another once there are enough of them, at sufficient complexity, to behave as a system — and it is why new capabilities and new failure modes tend to arrive together, as two faces of the same transition.
That distinction sets the governance problem. Capabilities that were never explicitly designed, and that were not visible in smaller or earlier systems, arrive this way. So do emergent risks: new failure modes, harmful interaction effects, and gaps between what a model was evaluated to do and what it does in real institutional settings. If a behavior is a property of a configuration rather than of a component, then examining components will not find it, and a scaling curve will not tell you when it appears.
The same logic holds one level up, and that is where this practice does its work. A deployed AI system is itself a set of interacting parts — the model, the people who act on its outputs, the records it reads and writes, and the institutional rules around all of them. That arrangement has emergent behavior too, and it is not the behavior of the model measured alone. Scaling does not simply improve performance. It can change what the system is, what it can do, and what it can get wrong.
So safety has to be assessed where the behavior actually is: in the whole arrangement, under real deployment pressure, on a schedule someone is accountable for. That calls for more than measuring performance after development. It calls for leadership that understands emergence, complex systems, and the governance structures needed to guide powerful technologies responsibly.
That is what Paramerge exists to do.
Go deeper
The method is not new. It runs from modeling single neurons to governing capable AI today, one approach applied at rising scale.
Research & engineering lineage · Papers and essays · Leadership · AI in the Room (community)
Work With Paramerge