Constructor Student Labs

Student Labs: Constructor Fabric Research Edition

Curious how AI is changing the way software is built? Want to explore it hands-on, guided by the researchers who work on it every day?

Constructor Tech and Constructor Labs, together with Constructor University, invite you to Student Labs: a 2-month educational research program for BSc and MSc students.

This edition is dedicated to Constructor Fabric, a shared AI and software platform. Fabric brings together reusable building blocks, common infrastructure and AI agents that help design, build and test software.

AI-native software platforms are one of the fastest-growing fields in tech, and few students get to study one from the inside. Student Labs gives you that chance. You explore open research questions on a platform in active development, learn current research methods, and build skills that are in high demand in industry and academia.

AI that builds software

• Domain-specific languages (DSL): how a formal language can describe software components so that AI can generate and regenerate them from specifications
• Neurosymbolic models: combining neural networks with logic and rules, so that AI-generated code can be checked, not just produced
• Rule extraction and fine-tuning: how to extract rules and knowledge from existing code and use them to adapt language models
• World models: how AI systems build an internal model of their environment to understand, plan and predict
• Formal verification: mathematical methods that prove software behaves as specified
• Geometric models: using geometry to represent data and help AI models learn from it
• Benchmarking: how to measure fairly whether one AI model or method is really better than another

Next-generation language models

• Diffusion models for text: today’s LLMs write one token at a time, which makes them slow and prone to hallucinations. Diffusion models generate whole passages at once. Explore how to make them match and beat today’s models.
• LLM security: how to host large language models securely when many users and organisations share the same system

• Explore an open research question that matches your level: beginner, intermediate or advanced
• Learn from weekly mentoring sessions with Constructor researchers and engineers
• Exchange ideas with other students, and study solo or in a pair
• Present your results as a research report, prototype or research concept

• BSc and MSc students of Constructor University and our partner universities
• Students with a strong interest in AI, LLMs, software engineering or research. Beginners are welcome!

1. Choose a topic from a curated list proposed by our researchers.
2. Find your level. Topics are offered for beginner, intermediate and advanced students, so everyone can find one that fits.
3. Study solo or in a pair, depending on the topic.
4. Lead your own research and set your own schedule, with weekly guidance from your mentor.
5. Present your results and receive feedback and a certificate of completion.

• Study a fast-growing field from inside a real AI platform
• Learn from experts: weekly mentorship from researchers and engineers
• Earn academic credit: depending on your university’s rules, the Labs can count towards your mandatory internship, earn you project credits, or become part of your thesis
• Publish: strong results can be published, with you as an author
• Build your research portfolio and receive a certificate
• Next steps: thesis co-supervision, and you can apply for paid internships in the Constructor ecosystem (separate application)

📅 Duration: 2 months
📍 Format: remote, or hybrid in Bremen (DE), Sofia (BG) or Belgrade (RS)
🗓 Mentoring: weekly sessions with your mentor. About 10–15 hours a week; you set your own schedule.

Student Labs is an educational research program, not a job or an internship. Participation is unpaid and voluntary.