Senior Data Scientist, Predictive Maintenance System

This is a fully remote position, open to applicants in Ukraine.

📋 Description

• Analyze historical data related to equipment, maintenance, operations, sensors, and telemetry to uncover trends linked to equipment degradation and failures.

• Collaborate with domain experts to comprehend failure modes, their potential indicators, and assess whether the available data offers adequate predictive signals.

• Conduct exploratory data analysis, data profiling, statistical analysis, correlation analysis, and feature discovery.

• Evaluate data quality, completeness, frequency, and predictive value prior to model development.

• Identify and engineer pertinent features from time-series and operational data.

• Create, train, validate, and optimize machine learning models for failure prediction, anomaly detection, and predictive maintenance.

• Assess suitable modeling techniques for various equipment and failure scenarios.

• Define appropriate model evaluation metrics and verify model performance against business and operational goals.

• Develop strategies for managing imbalanced datasets and rare failure occurrences.

• Partner with Data Engineers and solution architects for data preparation and model integration.

• Work alongside equipment and maintenance subject matter experts (SMEs) to confirm model outputs and ensure predictions are meaningful in operational contexts.

• Assist in model explainability and offer transparency into the key factors influencing predictions.

• Document experiments, assumptions, data limitations, model performance, and recommendations.

• Aid in transitioning validated models from experimentation or proof of concept into a production-ready solution.

⛳️ Requirements

• A minimum of 5 years of experience in Data Science or Machine Learning, ideally encompassing predictive maintenance, industrial analytics, or IoT applications.

• Strong expertise in Python and widely-used data science libraries such as Pandas, NumPy, and Scikit-learn.

• In-depth knowledge of machine learning, statistical analysis, time-series analysis, anomaly detection, classification, regression, feature engineering, and model validation and optimization.

• Proficiency in working with sensor, telemetry, event, and time-series datasets.

• Familiarity with predictive maintenance principles, including failure prediction, condition monitoring, and equipment health indicators.

• Experience managing missing, noisy, sparse, and imbalanced industrial data.

• Strong SQL and data analysis capabilities.

• Experience with model explainability and effectively communicating model results to both technical and business stakeholders.

• Ability to collaborate closely with engineering and domain SMEs to convert physical equipment behavior into analytical hypotheses.

• Previous experience in manufacturing, industrial equipment, IoT, vending or cooling equipment, or connected-device analytics.

• Experience with cloud-based ML and data platforms.

• Familiarity with Azure Machine Learning, Databricks, MLflow, or similar technologies.

• Knowledge of MLOps and production model monitoring.

• Experience with streaming or near-real-time telemetry.

• Understanding of Remaining Useful Life modeling and survival or reliability analysis.

• Experience with deep learning techniques for time-series data.

🏝️ Benefits

• Health insurance from the first day of employment, regardless of the probationary period.

• Christmas holidays from December 25 to December 31.

• Collaboration with the Superhumans center and Veteran HUB.

• Access to psychological counseling provided by the Veteran Hub.

• Internal policies that foster a company culture supportive of military personnel and veterans.

• Support for psychological rehabilitation initiatives.

• Permanent contract offered.