<p><strong>Supervisor: </strong>Prof.
Alexander Tormasov<strong> </strong></p> <p><strong>.
Constructor Knowledge Labs (CKL), in collaboration with Constructor Technology, invites applications for a PhD position in machine learning for software engineering and formal methods, on the Constructor Fabric project.
Constructor Fabric turns a company's informal knowledge into production software through a pipeline of composable capability units called gears:
We are building a <strong>World Model</strong> over that pipeline — a model that does not just generate code, but predicts the <em>consequences</em> of an architectural decision: total cost of ownership, unintended side effects, latency and failure behaviour, and whether a proposed composition is even admissible.
</p> <p><br>The central object is not a digital twin of the application but its <strong>formal architectural skeleton</strong>: gear contracts (GearSpec), a typed attributed hypergraph of the application (AppGraph), a composition algebra that defines which assemblies are legal, and several semantic projections (types, protocols, resources, security) over which properties are proved, refuted by counterexample, or reported as an explainable <strong>gap</strong>.
All of it is written in a <strong>domain-specific language</strong> whose syntax trees and graphs we keep in a projectional editor (JetBrains MPS) — so the DSL is not a convenience layer, it is the thing that defines the model's state space and the boundary of what the model is allowed to propose.
</p> <p><strong>What you will work on</strong><br>Depending on your background, one or two of:</p> <ol> <li>Formal skeleton and composition — GearSpec as a contract $(Requires, Provides, State, Effects, Assumptions, Guarantees, Parameters)$; AppGraph as a typed attributed hypergraph; an algebra of assembly (sequential, paral.