As a Senior Data Scientist (Manufacturing & Process AI), you will build and deploy machine learning models directly on plant data to significantly cut energy consumption, improve critical equipment reliability, and tighten product quality across our operations.
This is a highly collaborative, hands-on modeling role embedded within our process, operations, and reliability teams. Your success will be measured by finance-validated operational savings (e.g., kcal/kg clinker, kWh/tonne, and avoided downtime).
Key Responsibilities
- ML Modeling for Industry: Build, validate, and deploy ML models for process optimization (kiln/pyro-process control, grinding & separator efficiency), predictive maintenance on critical rotating equipment, and quality/clinker-factor optimization.
- Industrial Data Wrangling: Work with high-frequency sensor and time-series data from plant historians, DCS, and IIoT systems. Clean and engineer meaningful features from noisy, real-world industrial signals.
- Bridge the Gap (OT to AI): Partner closely with plant operators and process engineers to encode domain knowledge into your models. Safely guide models from advisory recommendations toward closed-loop control.
- Business & Financial Rigor: Establish rigorous baselines and quantify financial impact with institutional discipline, defending data results under scrutiny.
- Production Deployment: Collaborate with the MLOps/Platform team to productionize models and monitor their drift and performance in live operations.
Required Qualifications & Skills (Must-Have)Education & Experience
- Degree: Bachelor's or Master’s degree in Engineering (Chemical, Mechanical, Electrical, Industrial), Statistics, Computer Science, or a related quantitative field.
- Experience: 3–6 years of experience building and deploying ML models, with demonstrable experience in a manufacturing or process-industry environment (e.g., cement, steel, refining, chemicals, power, glass, mining).
Technical Skill Set
- Core Machine Learning: Deep command of classical machine learning including regularized regression (Ridge, Lasso, ElasticNet), tree-based ensembles (Random Forest, XGBoost, LightGBM, CatBoost), SVM, k-NN, and Naive Bayes.
- Data Science & Engineering: Strong, idiomatic Python (NumPy, pandas, SciPy, scikit-learn, statsmodels) writing clean, tested, production-quality code. Strong SQL skills are mandatory.
- Time-Series & Analytics: Strong applied skills in time-series analysis, sensor/signal data processing, anomaly detection, regression, and forecasting with a solid statistics foundation.
- Soft Skills: Comfortable being on the plant floor, explaining complex models simply to engineers and operators to earn their trust.
Preferred Qualifications (Strong Plus)
- OT Data Experience: Hands-on experience with Industrial IoT (IIoT) and Operational Technology (OT) data—plant historians (OSIsoft PI / AVEVA, Aspen IP.21), OPC-UA, SCADA / DCS, and time-series databases.
- Domain Exposure: Background in cement or heavy/process manufacturing (pyroprocessing, grinding, combustion, quality control).
- Enterprise Systems: Experience working with data from SAP (ERP—specifically PM/PP modules) and Salesforce (SFDC).
- Advanced Controls: Familiarity with Advanced Process Control (APC) concepts and closed-loop deployment.
- Advanced Modeling: Deep learning for time series; physics-informed or hybrid (data + first-principles) modeling.
- Big Data: Experience with PySpark for large datasets.
Technical Environment & Tools
- Programming: Python (pytest, OOP), SQL, Jupyter, Git
- Libraries: Scikit-learn, Statsmodels, XGBoost, LightGBM, Matplotlib, Seaborn, sktime, tsfresh, Prophet
- Unsupervised: K-means, DBSCAN, Hierarchical Clustering, PCA
- Platforms: Cloud/Lakehouse (Azure, AWS, or Databricks), Git-based workflows.
Pay: Up to ₹1,200,000.00 per year
Application Question(s):
- Notice Period / Joining Timeline:
This is an urgent requirement. Are you available to join within immediate to 1 week maximum?
Options: Yes / No
- This position is being filled as a Vendor Contract role. Are you comfortable working under a vendor contract engagement?
Options: Yes / No
- Do you have demonstrable experience building and deploying ML models specifically within a manufacturing or heavy process-industry environment (e.g., cement, steel, refining, chemicals, power, glass, mining)?
- current salary per month?
- expected salary per month?
Experience:
- Senior Data Scientist (Manufacturing & Process AI): 3 years (Required)
Work Location: In person
