Junior Data Scientist

About us

Recupere Metals has developed a new wire-forming technology that produces high-conductivity copper wire without the need for 99.95% pure copper raw materials. No smelting. No refining. Just a smarter process using only scrap copper.

By eliminating these costly and highly polluting steps, we are considerably reducing the overall cost of copper-wire production while putting to use millions of tonnes of copper scrap currently unsuitable for electrical use. Our technology paves the way for fully circular and cost-effective copper-wire production, an essential piece of the global energy transition.

We have raised over EUR5m in our first round of funding from leading investors, secured strong interest from large commercial offtakers, and demonstrated that we have a way of boosting the world's production of recycled copper.

We're building our R&D team, and it's the perfect time to jump on board.

About the role

We are looking for a Junior Data Scientist / ML Engineer to take on the day-to-day challenges of a deep-tech startup: a dataset that is still growing, models that need to be improved through sound data science, and a data processing pipeline we want to enrich with concepts from Integrated Computational Materials Engineering (ICME) and Materials Informatics.

This is an R&D position, supervised by our ML Engineering Lead. We work with a research mentality: our goal is to develop professionals with the critical thinking needed to contribute across the different fronts of our business. The expected path is that you first understand the process, then follow the direction set by the ML Lead and the CTO, and over time grow into a mid-level role where you own internal projects and make your own technical decisions.

At 3 months, we expect the candidate to be confirmed as a permanent hire, with a general understanding of the processes currently running at the company and clear visibility into the roadmap of the project(s) they will own. They should be able to carry their tasks through the following semester guided by the ML Engineering Lead.

At 6 months, we expect them to have built the foundation of our characterization system project, which will be delegated to them. At this stage, the person will already have developed enough autonomy to propose solutions based on their interaction with the material scientists.

At 12 months, we expect the person to be the full owner of these projects and to begin progressing toward a mid-level Data Scientist /ML Engineer role, with the ability to understand and engage with other areas of the company's ML work.

Our hiring process has three stages.

• Introductory conversation — to understand the candidate's motivations and assess fit, career expectations, and how they see themselves growing within the company.
• Technical case — for shortlisted candidates, a technical conversation built around a case study, which will be sent to the candidate two days ahead of the technical interview.
• Founder conversation — an alignment conversation with at least one of our founders, giving the candidate broader, more personal context about the company and the chance to meet people from other areas, beyond the technical side.

What you will work on

• Materials science interface. You will work alongside our materials engineering team, helping translate their scientific findings into features and models that ultimately feed our production models and our industrial controller.
• Characterization methods. You will help implement and improve the characterization methods used during our material process, applying symbolic regression and other ML and data science techniques.
• Feature engineering from domain knowledge. You will turn qualitative materials science insight into measurable, quantitative features that can be integrated into our final models and controllers.
• Benchmarking and iteration: comfort evaluating model performance against the approaches we currently use and against relevant baselines, and helping establish the benchmarks we use to measure progress.
• Company-wide ML exposure (10–20% of your time). You will spend part of your time understanding the other ML developments across the company. This is a deliberate part of your development: you will be exposed to ML engineering and MLOps concepts, built on top of the knowledge you already have. Given the nature of the project, we want you to have the big picture of the company and its objectives, so that you can gradually propose solution