Job Specifications
About us
Over the past few months, and with a founding team consisting of Julien, a PhD in materials science, and Katie, a former business development manager at a climate technology company, we have raised our first round of funding from leading investors, secured several letters of intent and demonstrated that we have a way of boosting the world's production of recycled copper.
We have 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.
By eliminating these costly and highly polluting steps, we are considerably reducing the overall cost of copper wire production, while making use of 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, making it an essential part of the global energy transition.
We’re now building our core team, and it’s the perfect time to jump on board.
About the role
We are looking for a Machine Learning Engineer with a strong background in deep learning for predictive process control, to help us model and optimize our novel mechanical and thermal wire forming process.
You’ll take the lead on developing a model-based controller capable of anticipating system behavior and driving performance improvements in real-time. Your work will sit at the intersection of physical process modeling, data-driven algorithms, and real-world industrial systems.
Contract: CDI (permanent)
Location: Nanterre (hybrid)
Language: English fluency required. French is a plus but not required.
Your responsibilities
Develop and deploy predictive control algorithms to optimize mechanical and thermal processes for wire forming
Build hybrid models using deep learning and physics-based insights, incorporating process data and literature-based proxies
Design and implement efficient data collection pipelines from characterization methods to support model training and validation, to gather an optimized dataset
Simulate process dynamics, stress-test control logic, and run live tests on physical prototypes
Ensure the system is robust to uncertainties and ready for industrial scale-up
Ideal background
Engineering degree, MSc or PhD in Machine Learning, Control Engineering, Applied Mathematics, Physics, Material Science or related field
Strong hands on experience in model-based controlling and reinforcement learning for process control/material characterization
Proven track record applying deep learning to real-world physical systems
Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow, C++)
Familiarity with simulation tools (e.g., Abaqus, Ansys, Simulink, Modelica, or custom simulation environments)
Bonus: Experience working with manufacturing systems or industrial process control
Bonus: Demonstrated initiative in building and experimenting, whether through side projects, small-scale physical prototypes, or hands-on tinkering in a garage or lab
What we offer
We’re building a world-class industrial deep tech company, and we’re doing it from the ground up. You’ll be one of the earliest team members, shaping not only the tech, but the culture, direction, and impact of our start-up.
CDI contract
Competitive compensation + BSPCE package
50% health insurance coverage
Hybrid work model (office in Nanterre)
We believe deep tech needs deep diversity. We’re committed to building an inclusive, impact-driven team, and if you’re excited by our mission but don’t tick every box, we’d still love to hear from you. We value versatility and the ability to learn, which is absolutely essential at this stage of our business.
Let’s build the future of circular copper, together.
About the Company
Marble is a climate tech venture studio solving hard climate problems. Our mission: bring us at least one gigaton closer to net zero and create a future that thrives.
We do this by partnering with scientists, engineers and operators to build deeptech startups that slash emissions, remove carbon, and cool the planet.
The climate crisis is the most pressing challenge of our times. Solving it requires breakthrough technology, as available solutions only get us halfway. We can’t put all our hopes in classic tech transfer. We n...
Know more