Internship position for World Models for Software Architecture (Constructor Fabric) — Opportunihub
Job

Internship position for World Models for Software Architecture (Constructor Fabric)

Constructor Labs · Africa

At a glance

Type
Job
Organisation
Constructor Labs
Location
Africa
Work mode
On-site
Deadline
Rolling / not stated
Posted
14 Oct 2026

About this job

&lt;p&gt;&lt;strong&gt;About the Project&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Constructor Fabric turns a company&#39;s informal knowledge into production software through a pipeline of composable capability units called &lt;em&gt;gears&lt;/em&gt;: requirements → architecture → product fit → framework (G1) → application → runtime. We are building a &lt;strong&gt;World Model&lt;/strong&gt; over that pipeline — a model that does not just generate code, but predicts the &lt;em&gt;consequences&lt;/em&gt; of an architectural decision: total cost of ownership, unintended side effects, latency and failure behaviour, and whether a proposed composition is even admissible.&lt;br&gt;The central object is not a digital twin of the application but its &lt;strong&gt;formal architectural skeleton&lt;/strong&gt;: 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 &lt;strong&gt;gap&lt;/strong&gt;. All of it is written in a &lt;strong&gt;domain-specific language&lt;/strong&gt; 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&#39;s state space and the boundary of what the model is allowed to propose.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Internship Role&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;As a Research Intern (Machine Learning for Software Engineering), you will support the data and modelling work behind the World Model — mining code, building datasets, and running baseline experiments. We are looking for students who are keen to collaborate with industrial companies working with AI, open to out-of-the-box topics, and interested in a long-term collaboration.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Key Responsibilities&lt;/strong&gt;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;Mine open-source repositories and extract architecture, dependency, and interface graphs from code.&lt;/li&gt; &lt;li&gt;Help build and clean (specification → architecture) datasets, including synthetic project generation.&lt;/li&gt; &lt;li&gt;Implement and evaluate baseline models (heuristic search, graph ML, or LLM generation) for single pipeline steps.&lt;/li&gt; &lt;li&gt;Benchmark models against shared datasets and metrics to compare approaches.&lt;/li&gt; &lt;li&gt;Build evaluation harnesses and track experiments reproducibly.&lt;/li&gt; &lt;li&gt;Assist with documentation and, where relevant, publication activities.&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&lt;strong&gt;Required Qualifications&lt;/strong&gt;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;Currently enrolled in a BSc/MSc in Computer Science, Data Science, Mathematics, or similar.&lt;/li&gt; &lt;li&gt;Experience with Python and ML frameworks (PyTorch, scikit-learn).&lt;/li&gt; &lt;li&gt;Interest in machine learning for code, software engineering, or formal methods.&lt;/li&gt; &lt;li&gt;Good English and teamwork skills.&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&lt;strong&gt;Desired Qualifications&lt;/strong&gt;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;Predictive models/time-series/etc.&lt;/li&gt; &lt;li&gt;LLM tooling.&lt;/li&gt; &lt;li&gt;Familiarity with graph machine learning (PyTorch Geometric or DGL).&lt;/li&gt; &lt;li&gt;Interest in formal methods, program or static analysis, or working with code structure (e.g. AST manipulation, tree-sitter, or repository mining).&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&lt;strong&gt;Application Details&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Please submit:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;CV&lt;/li&gt; &lt;li&gt;Short motivation letter (max. 1 page) explaining your interest and relevant skills&lt;/li&gt; &lt;li&gt;Transcript of records (GPA obligatory)&lt;/li&gt; &lt;/ul&gt;<p>Find <a href="https://www.arbeitnow.com">Jobs in Germany</a> on Arbeitnow</a>

How to apply

  1. 1 Read the full details above and confirm you meet the eligibility criteria.
  2. 2 Prepare your documents — an updated CV, and any cover letter, proposal or certificates required.
  3. 3 Click Apply on official site to complete your application on Constructor Labs’s official page.
  4. 4 Submit as early as possible — many close once filled.
Apply on official site

Sourced from arbeitnow. Always verify details on the official website. Opportunihub never charges you to apply.

Frequently asked questions

How do I apply for Internship position for World Models for Software Architecture (Constructor Fabric)?

Review the full details and eligibility on this page, prepare your documents, then use the “Apply on official site” button to complete your application on Constructor Labs’s official page.

Is this opportunity remote or location-based?

This opportunity is based in Africa. Check the official listing for any relocation or on-site requirements.

Is Internship position for World Models for Software Architecture (Constructor Fabric) free to apply for?

Opportunihub lists this Job for free. Legitimate Jobs do not ask for payment to apply — never pay a fee to submit an application.