We are looking for a Senior Data Scientist to lead the development of machine learning solutions powering real-time decision-making and recommendation systems in industrial production environments.
This is a hands-on role with end-to-end ownership. You will be responsible for the full modeling lifecycle, from problem framing and data exploration to modeling, evaluation, deployment, and production impact. You will work with complex, noisy sensor and control data, building models that must be robust, interpretable, and reliable in real-world conditions.
You will collaborate closely with deep learning researchers, research engineers, and domain experts, and play a key role in shaping how data science is applied across the system.
Key Responsibilities
Design, develop, and evaluate machine learning models for real-time industrial applications
Own the end-to-end modeling pipeline, including problem formulation, data preparation, feature engineering, model development, evaluation, deployment, and post-production monitoring
Translate ambiguous production challenges into well-defined data science problems
Lead feature engineering and data exploration on complex sensor and control datasets
Define KPIs, evaluation frameworks, and experimentation strategies
Ensure model robustness over time, including monitoring, drift detection, and continuous improvement
Work closely with data and research engineers to bring models into production
Drive best practices in modeling, validation, and reproducibility
Communicate insights, trade-offs, and recommendations clearly to stakeholders
Requirements: B.Sc./M.Sc. in Computer Science, Statistics, Applied Mathematics, or related field
5+ years of hands-on experience applying machine learning in production environments
Strong Python skills and experience with ML libraries such as scikit-learn, XGBoost, LightGBM, or CatBoost
Proven experience with feature engineering, model selection, and evaluation in real-world scenarios
Strong statistical understanding and ability to reason under uncertainty
Experience working with messy, high-dimensional, or time-series data
Ability to independently own problems and drive them to production
This position is open to all candidates.