Data Scientist

Job Summary:

Data Scientist

You will play a key role in designing, developing, and deploying smart scheduling algorithms integrated with real-world constraints like machine availability, workforce planning, shift cycles, material flow, and due dates. 

Experience:

Responsibilities:

1. AI-Based Scheduling Algorithm Development

• Develop and refine scheduling models using: 
• Constraint Programming 
• Mixed Integer Programming (MIP) 
• Metaheuristic Algorithms (e.g., Genetic Algorithm, Ant Colony, Simulated Annealing) 
• Reinforcement Learning or Deep Q-Learning 
• Translate shop floor constraints (machines, manpower, sequence dependencies, changeovers) into mathematical models. 
• Create simulation environments to test scheduling models under different scenarios. 

2. Data Exploration & Feature Engineering

• Analyze structured and semi-structured production data from MES, SCADA, ERP, and other sources. 
• Build pipelines for data preprocessing, normalization, and handling missing values. 
• Perform feature engineering to capture important relationships like setup times, cycle duration, and bottlenecks. 

3. Model Validation & Deployment

• Use statistical metrics and domain KPIs (e.g., throughput, utilization, makespan, WIP) to validate scheduling outcomes. 
• Deploy solutions using APIs, dashboards (Streamlit, Dash), or via integration with existing production systems. 
• Support ongoing maintenance, updates, and performance tuning of deployed models. 

4. Collaboration & Stakeholder Engagement

• Work closely with production managers, planners, and domain experts to understand real-world constraints and validate model results. 
• Document solution approaches, model assumptions, and provide technical training to stakeholders. 

Qualifications:

• Bachelor’s or Master’s degree in: Data Science, Computer Science, Industrial Engineering, Operations Research, Applied Mathematics, or equivalent. 
• Minimum 1 year of experience in data science roles with exposure to: AI/ML pipelines, predictive modelling, Optimization techniques or industrial scheduling 
• Proficiency in Python, especially with: pandas, numpy, scikit-learn ortools, pulp, cvxpy or other optimization libraries, matplotlib, plotly for visualization 
• Solid understanding of: Production planning & control processes (dispatching rules, job-shop scheduling, etc.), Machine Learning fundamentals (regression, classification, clustering) 
• Familiarity with version control (Git), Jupyter/VSCode environments, and CI/CD principles 

Preferred (Nice-to-Have) Skills:

• Experience with: Time-series analysis, sensor data, or anomaly detection, Manufacturing execution systems (MES), SCADA, PLC logs, or OPC UA data, Simulation tools (SimPy, Arena, FlexSim) or digital twin technologies 
• Exposure to containerization (Docker) and model deployment (FastAPI, Flask) 
• Understanding of lean manufacturing principles, Theory of Constraints, or Six Sigma 

Soft Skills:

• Strong problem-solving mindset with ability to balance technical depth and business context. 
• Excellent communication and storytelling skills to convey insights to both technical and non-technical stakeholders. 
• Eagerness to learn new tools, technologies, and domain knowledge.