Middle (Middle+) Data Scientist / ML Engineer

We are looking for a full-time Middle Data Scientist / ML Engineer to join our team and take ownership of data-driven components in new products we are building from scratch.
 One of the first phases involves creating a data model of an industrial facility (digital twin) based on historical sensor and operational data, and developing predictive algorithms on top of it. The solution will include a data pipeline, a lightweight system model, forecasting modules, and integration with a simple dashboard.
This is a role for a specialist who communicates clearly, understands data deeply, and can work independently.

Responsibilities
 

• Analyse real industrial datasets and define structure, schemas and preprocessing logic.
• Build data pipelines and prepare clean datasets for modelling.
• Develop interpretable ML/time-series forecasting models.
• Participate in designing a simplified system model (data-driven “digital twin”).
• Prepare models for inference and assist with integration into backend services.
• Collaborate closely with PM and other team members, clarify requirements, and communicate modelling decisions.
• Produce clear, concise documentation for data and models.

Requirements
 

• 3+ years of experience as a Data Scientist or ML Engineer.
• Strong Python skills (pandas, scikit-learn; PyTorch/TensorFlow).
• Experience with time-series modelling or forecasting.
• Solid understanding of data cleaning, feature engineering and evaluation.
• Ability to work independently and take ownership of tasks without supervision.
• Good communication skills and ability to work with evolving or partially defined requirements.
• Experience with Docker and backend integration is a plus.

Nice to Have
 

• Experience with industrial or IoT data
• Experience with FastAPI or simple dashboards
• Understanding of model deployment workflows