About this role
Aperam is a global leader in stainless, electrical, and specialty steels, as well as recycling and renewables, serving customers in over 40 countries. Our business is structured into four segments: Stainless & Electrical Steel, Services & Solutions, Alloys & Specialties, and Recycling & Renewables.
We have a flat stainless and electrical steel production capacity of 2.5 million tonnes in Brazil and Europe, and we lead in alloys and high-value specialty products. Our industrial network includes 16 production facilities across Brazil, Belgium, France, the United States, India, and China. Aperam operates an integrated distribution, processing, and services network, with a unique ability to produce low-carbon stainless and specialty steels using biomass, stainless steel scrap, and high-performance alloys scrap.
Through BioEnergia, we produce charcoal from our own FSC®-certified forests, and with ELG - Aperam Recycling, a global leader in stainless steel and high-performance alloys recycling, we place sustainability at the core of our business, enabling our customers to thrive in the circular economy.
Join us and be part of a dynamic team where technology and innovation meets industrial transformation. Your talent and energy will help drive smarter, more sustainable solutions for a global company committed to be a leading value creator in the circular economy of infinite, world-changing materials.
Visit https://www.aperam.com/ to learn more - and let’s build what’s next, together.
Accountabilities Key Responsibilities
• Data Collection & Preparation • Gather large-scale industrial data from various sources, including IoT sensors, MES, SAP systems, and external data repositories • Clean, preprocess, and structure raw data to ensure accuracy and usability
• Exploratory Data Analysis (EDA) & Feature Engineering • Conduct exploratory data analysis to identify patterns, correlations, and anomalies in industrial processes • Develop and engineer new features to improve model performance and extract meaningful insights
• Model Development & Optimization • Select and implement appropriate machine learning algorithms for predictive maintenance, process optimization, and quality improvement • Train and fine-tune models, ensuring they generalize well to real-world scenarios • Evaluate models using performance metrics and validation techniques
• Deployment & Monitoring • Collaborate with IT and software engineering teams to deploy models into production environments • Monitor deployed models, detect performance drifts, and retrain models as needed
• Industrial Use Cases & Decision Support • Work on data-driven use cases such as quality, predictive maintenance, energy optimization, and supply chain forecasting • Support business and operational teams by providing insights and recommendations based on model outputs
• Collaboration & Communication • Work closely with cross-functional teams, including domain experts, business analysts, and industrial engineers • Translate complex data findings into actionable business insights, presenting them to both technical and non-technical stakeholders
• Coaching and mentoring • Coach and mentor junior data scientists (including GCC roles) on advanced data science/modelling techniques • Lead multiple data science projects and guide junior team members on each project
• Research & Continuous Improvement • Stay up to date with advancements in AI, machine learning, and industrial data science • Experiment with emerging technologies and methodologies to enhance data science capabilities within Aperam
Profile As a Data Scientist, you:
• Hold a Master’s or PhD in Data Science, Computer Science, Mathematics, or a related field • Have 7+ years of experience in data science, preferably in an industrial or manufacturing environment • Have led a team of junior data scientists and coached/mentored them in projects • Are proficient in Python, SQL, and machine learning libraries (Scikit-learn, TensorFlow, PyTorch, etc.) • Have strong experience in exploratory data analysis (EDA), feature engineering, and statistical modeling • Have a solid understanding of time-series analysis, predictive maintenance, and industrial AI applications • Are familiar with big data platforms and cloud environments (Azure, Databricks, Microsoft Data Fabric), and experience with Spark (PySpark or Scala) for big data processing is a plus • Have experience with data visualization tools such as Power BI, Matplotlib, or Plotly • Possess excellent problem-solving and analytical skills, with the ability to work on complex datasets • Have strong communication skills and can explain technical findings to non-technical audiences • Basic familiarity with the concepts of Computer Vision and Generative AI is a differential • Are fluent in English (both spoken and written); knowledge of French, or Dutch is a plus • Should be already working in the EU and ready to relocate to Genk