Data Scientist

We are looking for a Data Scientist who can work on real-world manufacturing and business problems using machine learning, statistics, and data engineering principles. The role is not limited to building models. You will work closely with product, engineering, and manufacturing domain teams to convert industrial data into actionable intelligence. You will contribute to: Forecasting production and demand Predictive maintenance Anomaly detection Optimization and recommendation systems KPI intelligence and root-cause analysis AI-driven decision support systems This is a hands-on role suited for someone who enjoys solving practical industrial problems rather than working only on academic datasets. Key Responsibilities Data Understanding & Preparation Analyze structured and semi-structured industrial datasets Clean, preprocess, and transform ERP, MES, IoT, and machine data Perform feature engineering for time-series and operational datasets Build reusable data pipelines for ML workflows Machine Learning & Analytics Develop predictive and prescriptive ML models Work on: Time-series forecasting Classification and regression Anomaly detection Optimization models Evaluate model performance and improve accuracy continuously Build explainable AI outputs for business users Business Problem Solving Translate manufacturing problems into analytical models Identify operational bottlenecks and performance drivers Work on OEE, downtime, scrap, throughput, energy, and supply chain analytics Support ROI-oriented decision intelligence Collaboration Work with backend engineers, frontend teams, and product stakeholders Collaborate with manufacturing experts to validate model outputs Participate in architecture and solution discussions Deployment & Monitoring Support deployment of ML models into production systems Monitor model drift and performance degradation Contribute to MLOps and model lifecycle management Required Skills Strong knowledge of Python Good understanding of: Pandas NumPy Scikit-learn SQL Understanding of machine learning fundamentals Experience with time-series analysis Knowledge of statistics and probability Familiarity with REST APIs and data integration concepts Cloud & Engineering Exposure Exposure to AWS or Azure Understanding of Docker and Git Basic understanding of data pipelines and microservices architecture Preferred Skills Experience with: PyTorch or TensorFlow Prophet / XGBoost / LightGBM TimescaleDB / PostgreSQL Stream processing or IoT data Manufacturing or industrial analytics exposure is a strong advantage What We Expect Strong problem-solving mindset Ability to work with ambiguous real-world data Curiosity to understand manufacturing operations Ability to communicate insights clearly Ownership mentality and startup adaptability What You Will Work On Predicting machine failures before breakdowns Forecasting production bottlenecks Dynamic line-capacity optimization Supplier risk intelligence Financial and operational KPI forecasting AI-assisted root-cause analysis Decision recommendation engines Why Join PlantNxt Build AI for real factories, not demo datasets Direct exposure to manufacturing leadership problems Opportunity to work across AI, cloud, product, and industrial systems High ownership and learning environment Opportunity to shape the core intelligence layer of the platform