Data Scientist

Your Role:

As a Data Scientist specialized in Condition Monitoring and automated data pipelines, you will contribute to the development of predictive and prescriptive maintenance solutions for connected industrial equipment.

Your mission will be to design, implement, and scale data science models that monitor the condition of machines in real-time, detect anomalies, and prevent failures. You will work at the crossroads of data science, software engineering, and IoT analytics.

Main Responsibilities:

* Analyze time-series data from IoT sensors (vibration, temperature, pressure, etc.) to develop condition monitoring models.
* Develop automated pipelines for data ingestion, preprocessing, and anomaly detection.
* Implement machine learning and statistical models to identify early signs of equipment degradation or failure.
* Collaborate with data engineers to deploy models into production, ensuring scalability and robustness.
* Build dashboards, APIs, and alerting systems to provide real-time insights to operations teams.
* Apply MLOps practices (CI/CD, model versioning, monitoring) to ensure reliable and repeatable model deployment.
* Document models, processes, and tools clearly and share with relevant teams (R&D, Operations, Maintenance).

Your Profile:

Education & Experience:

* MSc in Data Science, Applied Mathematics, Mechatronics, Computer Science, or related field.
* 2+ years of experience in Data Science or Machine Learning, ideally with a focus on IoT or industrial applications.
* Hands-on experience with at least one end-to-end project involving predictive maintenance or anomaly detection.

Technical Skills:

* Strong skills in Python (pandas, numpy, scikit-learn, etc.) and SQL
* Experience with time-series data and signal processing (Fourier transforms, filtering, frequency domain analysis)
* Familiar with IoT data streams, MQTT, or edge-to-cloud architectures is a plus
* Knowledge of anomaly detection, predictive maintenance, or condition-based monitoring models
* Experience with MLOps tools: MLflow, Airflow, Docker, Git, CI/CD pipelines
* Good understanding of real-time data processing tools: Kafka, Spark Streaming, or similar
* Experience deploying models via APIs (FastAPI, Flask) or on cloud/edge environments (AWS/GCP/Azure, Kubernetes)

Soft Skills:

* Strong problem-solving and analytical mindset
* Autonomy, curiosity, and a passion for innovation
* Comfortable working in cross-functional teams (data, engineering, maintenance)
* Ability to explain technical results to non-technical stakeholders