Builds the MVP of REON, an EPFL research spin-out in formation whose AI predicts the reuse value of building components before demolition. The engineer rebuilds the Python scoring engine, designs the database layer, migrates graph data from Neo4j, implements GNN similarity matching, and ships a web UI — a ~2-3 month fixed-term contract at EPFL in Lausanne.
REON is an EPFL research-based venture developed at the Structural Xploration Lab, building the Reuse Viability Index (RVI), an AI system that predicts the reuse value of building components before demolition, using data from more than 23,200 reuse-market listings and transactions. We are looking for a developer with entrepreneurial ambition and the ability to grow into a founding role, to turn the existing research prototype into a working MVP fast enough to support the next grant application round.
Main duties and responsibilities
- Rebuild the RVI scoring engine as clean, standalone Python code, implementing the validated indicator formulas correctly
- Design and build the database layer (schema and storage) and connect it directly to the RVI engine
- Migrate the graph representation from Neo4j to a Python-native structure
- Implement data-ingestion and similarity-matching logic that completes missing component information (GNN)
- Build the web interface: data upload in, ranked results out
- Work independently from rough goals to working software, using modern tooling (including AI coding assistants) to move fast
- Keep the codebase clean and documented so it can be extended by others.
Profile
- Full-stack: able to own backend, data layer and frontend as one coherent system (upload data, run scoring, show ranked results).
- Degree in computer science, software engineering, data science, machine learning, or an equivalent field; recent graduates welcome.
- Strong Python skills; experience with APIs, databases, data pipelines, testing and deployment.
- Has personally built and shipped at least one complete software product or system beyond coursework.
- Able to translate research or mathematical logic into reliable software.
- Uses AI coding tools effectively, but independently reviews, tests and takes full responsibility for the resulting code.
- Graph data, ML/GNN, and LLM experience is a strong advantage.
- Ability to parse and work with structured building-data formats (BIM/IFC), or equivalent experience ingesting structured technical data from PDF/Excel sources
- Civil engineering or broader construction-industry background is an advantage, not required.
- Valid Swiss work permit is mandatory. Applications without one will not receive a response.
- Priority will be given to candidates already based in Canton Vaud or the Lausanne region, available to start immediately.
We offer
- The chance to build the technical core of an EPFL spin-out in formation, in circular construction and AI
- Direct collaboration with the founder and real ownership of what you build
- A flexible, hands-on role with genuine impact
- Location: EPFL, Lausanne.
- Employment rate: 60–80%.
- Fixed-term contract, approximately 2–3 months.
- Start date: ASAP. Applications reviewed on a rolling basis — the position may be filled before any closing date.
- Continued involvement possible if further REON funding is secured.