What exactly should you look for?

Core expertise: Python + Machine Learning + Time-Series Modelling + Numerical Optimization Industry preference: Manufacturing, Metals, Mining, Cement, Chemicals, Oil & Gas, Process Industries. A. Strong Python and Machine Learning

Must have

- Python programming.
- Machine Learning model development.
- LightGBM.
- GAM (Generalized Additive Models).
- Feature engineering.
- Model validation and diagnostics.
- Model explainability. The candidate should be capable of reviewing existing models and improving them rather than building everything from scratch. B. Time-Series and Industrial Process Modelling Critical skill This is one of the most significant parts of the requirement.
- Time-series forecasting and modelling.
- Industrial process data.
- Equipment performance modelling.
- Historian data and laboratory data.
- Lagged features and sensor data.
- Process variables and operational parameters.
- Predictive modelling for manufacturing operations. What does this mean practically? The candidate should understand how these variables interact and build models that predict the final outcome. C. Constrained Numerical Optimization.
- Numerical optimization.




- Constrained optimization.
- Metaheuristic algorithms.
- Grid Search.
- Optimization of operating parameters.
- Multi-objective optimization.
- Throughput, recovery and cost optimization.
- Sensitivity and scenario analysis. D. Industrial Domain Experience
- Manufacturing.
- Mining and Metals.
- Cement.
- Chemicals and Petrochemicals.
- Oil & Gas.
- Power and Energy.
- Industrial Automation. Experience working with process engineers, plant operators, operational SMEs and industrial data. A candidate with experience in manufacturing optimization or process optimization would be particularly relevant. E. Model Pipeline and Live Testing Look for candidates who have worked on:
- ML model pipelines.
- Model deployment and inference workflows.
- Kedro (QuantumBlack) desirable, not mandatory.
- API integration and data exchange.
- Live model validation.
- Shadow testing.
- Model monitoring and feedback loops. The candidate should be comfortable running predictions on live plant data and comparing them with actual outcomes.

📌 Data Scientist (Bengaluru)
🏢 CoffeeBeans Consulting
📍 Bengaluru