Kurt Sys

Kurt Sys, B.Eng. - Software Architect, QA Engineer, Tech Lead at Vintecc

Exploiting Uncertainty Outside the Model: Industrial ML as a Hyperliminal Systems Problem

Abstract: In academic data research, exploiting uncertainty is mostly a concern within the model itself: calibrated posteriors, active learning, optimal experimental design. This talk is about where to embed the model: exploiting uncertainty outside the model, in the environment where the model is deployed. Industrial deployments are hyperliminal systems: environments where external forces (stressors) cannot be fully enumerated in advance, where requirements change faster than they can be specified, and where even a perfectly calibrated model still fails because the world around it has changed and there is always “that one exception we didn’t think of.” In that context, uncertainty is not a property to be minimized; it is the signal that drives every interesting design decision in the system.
The real engineering work, then, is designing the software around the model—the interfaces, the observability, and the organizational hooks. The system should encapsulate the model and shield it from a complex and often uncontrollable environment. That means thinking carefully about how guidance and explanations reach the user, accepting that you can never fully trust an end user to interpret a result correctly, and treating every analysis as a default lie until the surrounding system proves it true. Those default lies are not a flaw to be designed out; they are the load-bearing assumption that keeps the design honest, and the driving force behind every robust and resilient industrial system we build.

Biography: Kurt is a recovering microbiological systems engineer. At Vintecc, he is the tech lead and architect on the Data & AI Ops team: broadly speaking, the infrastructure surrounding the model that nobody asks for but everyone needs. Previously: he kept astronauts alive during long-term space travel using microbiological life support systems, where the microbiology is inherently complex but the environment is controlled and bounded. Currently: he keeps analytical models running on factory floors, where the model is simple but the environment is anything but. He says the latter is harder.

‍