You will represent and communicate data requirements to help us understand our data assets and the relationships among them. You will investigate, analyze and scope data requirements to support the development of data integration, data retrieval and reusable data sets.

Analyze business requirements as a guide for data modeling and apply data analysis, design, modeling, and quality assurance techniques, based on a detailed understanding of business processes, to establish, modify or maintain data structures and associated components (entity descriptions, relationship descriptions, attribute definitions

Advise on the details of data structures and associated components

Manage the iteration, review and maintenance of data requirements and data models and you will assist in creating the sematic layer of data

Have cross-functional understanding to create reusable data assets

Choose a suitable data modeling approach for each project, such as by assessing the suitability of existing data models and build data models with the flexibility to change when business requirements change

Reconcile multiple logical source models into a single, logically consistent model and you will ensure that the proposed model follows data architecture guidelines and best practices

Rationalize the relationships expressed in the logical data model to the schema of the physical data store (that is, database tables and columns)

A desire to drive your future and accelerate your career and the following experience and knowledge:

Extensive experience in data modeling in a large complex business with multiple systems

At Mondelēz International, data science is a critical accelerator in our mission to lead the future of snacking. We are looking for a Data Scientist to join our ISC Central Analytics team and strengthen the data-science capability across our Integrated Supply Chain — with a primary focus on Quality and Food Safety analytics and support / scale our Manufacturing Data Science practice.

You will sit at the intersection of quality, food safety, and manufacturing operations, building AI, machine-learning, NLP, GenAI, computer-vision, optimisation, and simulation solutions that make our supply chain smarter, safer, and more resilient. The quality dimension is your home base — QCMS performance, audit readiness, QFS intelligence, compliance risk — but you will also extend the Central Analytics team's manufacturing data-science portfolio by helping scale predictive maintenance, process optimisation, and IIoT-driven analytics across the plant network.

Your work will transform quality, food-safety, and manufacturing data into production-ready intelligence that reduces Quality & Food Safety defects, non-conformances, compliance risk, RM/PM yield loss, unplanned downtime, and cost — while improving throughput, Customer Service Level (CSL), asset reliability, and operational efficiency.

Quality Control Management System (QCMS) — Primary Focus

Build quality prediction models for product-quality outcomes (CTQ and CTP parameters), supplier quality risk, defect probability, non-conformance risk, process drift, and first-pass yield across Biscuits, Chocolate, Gum & Candy categories.

Develop QCMS audit-score prediction models to anticipate internal and audit outcomes, identify likely findings, quantify site-level quality risk, and prioritise preventive actions ahead of audits.

Create Quality Intelligence using NLP, clustering, causal analysis, and machine learning to classify non-conformances, identify recurring root causes, predict recurrence, score effectiveness, and predict closure delays — aligned with Mondelēz CAPA and Quality Policy (QP) frameworks.

Build analytics for hazards, hygienic zoning, food safety, pathogen monitoring, environmental monitoring, sanitation, allergen control, and cross-contamination risk in line with the Mondelēz HACCP Standard, Hygienic Zoning Programmes, and Prerequisite Programmes (PRPs).

Develop calibration and measurement-system analytics for calibration overdue risk, instrument drift, measurement uncertainty, compliance gaps, and quality impact from calibration failures.





Use NLP and GenAI to extract insights from QCMS audit reports, CAPA narratives, consumer complaints, deviations, SOPs, HACCP/Food Safety Plans (FSP), maintenance logs, and supplier communications; enable AI-assisted quality investigations and audit preparation.

Build analytics connecting supplier quality, incoming-material risk, and customer-quality outcomes to create end-to-end quality visibility across the supply chain — from raw material to consumer.

Build quality dashboards, risk scorecards, alerts, and self-service analytics for Q&FS;, BU Quality, Global Food Safety, Plant Operations, and RDQ stakeholders.

Manufacturing Data Science — Core / Supporting Focus

Build IIoT-enabled analytics using data from PLCs, SCADA, historians, MES , sensors, edge devices, vision systems, LIMS, and QMS platforms.

Develop predictive-maintenance models for equipment failure, asset health, remaining useful life, condition-based monitoring, anomaly detection, and maintenance prioritisation — leveraging IL6S (Integrated Lean Six Sigma) loss-elimination methodology.

Apply statistical process control, process-capability analysis (CpK/PpK), design of experiments, and root-cause methods (8D, 5-Why, FMEA) to reduce variation and improve yield — in partnership with the Process Excellence and Supply Chain Excellence teams.

Build mathematical optimisation and simulation models for production scheduling, line balancing, capacity planning, material flow, quality-resource allocation, sanitation scheduling, and calibration planning.

Support Deployment & Industrialization of models to cloud, edge, or on-premise environments with monitoring, retraining, governance, and auditability.

Platform, Data & Delivery

Partner with Q&FS;, BU Quality, Global Food Safety, RDQ, Manufacturing, Supply Chain Excellence, CS&L;, Process Excellence, Engineering/Maintenance, Procurement, HSE, and MDS (Mondelēz Digital Services) teams to define high-impact use cases and measurable success criteria.

Design, build, validate, deploy, and continuously improve ML, statistical, NLP, computer-vision, optimisation, simulation, and GenAI solutions using Databricks and Azure/AWS .

Design and implement scalable, secure, and governed data architectures and data-science solution patterns on Azure/AWS in collaboration with the AI, Data & Analytics Platform team.

Integrate data from SAP S/4HANA, SAP ECC, MES, SAP EWM, o9, IMS, QMS/eQMS (QCMS), food-safety systems, audit tools, and IIoT platforms into reliable Databricks-based data products — leveraging Collibra / Ataccama for data governance and MuleSoft / SAP BTP for integration.

Build real-time dashboards, alerts, scorecards, and self-service analytics using Tableau, Power BI, Databricks SQL, or Python-based tools for Q&FS;, plant, and ISC stakeholders — feeding into Executive dashboards and KPI reporting where applicable.

Quantify business impact through MDLZ-specific quality, food-safety, manufacturing, and supply-chain KPIs.

5–8+ years of experience in quality analytics, food-safety analytics, manufacturing analytics, supply-chain analytics, industrial AI, or data science in an operational/FMCG environment.

- Hands-on, production-level experience with Databricks and Strong cloud experience (Azure and/or AWS) is required, particularly across data engineering, data-science solutioning, and solution architecture.
- Strong Python skills, including pandas, NumPy, scikit-learn, time-series libraries, and TensorFlow or PyTorch.
- Strong SQL, PySpark, and experience building scalable data pipelines and governed data products in Databricks.
- Strong foundation in machine learning, statistics, time-series analysis, anomaly detection, classification, regression, forecasting, and model validation.




- Experience designing end-to-end data-science and data-engineering architectures on cloud, including ingestion, storage, processing, feature engineering, model training, deployment, monitoring, and governance.
- Experience building dashboards using Tableau, Power BI, Grafana, Databricks SQL, or Python-based tools.
- Experience working with QMS/eQMS, IMS, MES, SAP ERP, CMMS, historians, IIoT platforms, or audit-management systems.
- Strong stakeholder-management, communication, and data-storytelling skills — comfortable presenting to both plant-floor teams and senior ISC leadership.

Knowledge of quality and food-safety frameworks such as HACCP, GMP, PRPs, Hygienic Zoning, allergen control, environmental monitoring, sanitation controls, and CAPA — familiarity with MDLZ Quality Policies (QPs) is a plus.

Knowledge of Manufacturing & Domain Frameworks such as Industry 4.0, IoT telemetry, Data Vault 2.0, and statistical process control (SPC) is a plus.

Experience with NLP techniques such as text classification, named-entity recognition, topic modelling, embeddings, semantic search, and retrieval-augmented generation.

Experience with computer vision, image processing, object detection, segmentation, and defect classification in manufacturing or food-production environments.

Experience deploying GenAI solutions using LLMs, vector databases, prompt engineering, and responsible-AI guardrails.

Exposure to IL6S (Integrated Lean Six Sigma), SPC, CpK/PpK, MSA, 8D, 5-Why, FMEA, and structured root-cause analysis.

Experience with MLOps, MLflow, model registries, data drifts, feature stores, streaming analytics, edge deployment, and Collibra-based or Ataccama-based data governance.

Understanding of manufacturing and supply-chain systems including SAP S/4HANA, SAP ECC, SAP EWM, o9 (IBP/S&OE;), MES , CMMS, APS, TMS, LIMS, QMS/eQMS, IOT, Connected Worker and industrial historians.

Bachelor's or Master's degree in Data Science, Computer Science, Industrial Engineering, Chemical/Mechanical/Electrical Engineering, Food Science, Statistics, Operations Research, or a related field.

Master's degree or advanced qualification in Data Science, AI, Industrial Engineering, Quality Engineering, Food Safety, or Operations Research is preferred.

Databricks Data Engineer, Machine Learning, or Generative AI Engineer certification.

Azure Data Scientist / Engineer Associate, or AWS Certified Machine Learning – Specialty / Data Engineer – Associate / Solutions Architect or equivalent.

Quality & Food Safety

Reduced consumer complaints, non-conformances, quality escapes, and quality-related holds.

Reduced food-safety risks through sanitation, pathogen-monitoring, hygienic zoning, and environmental-monitoring analytics.

Reduced RM/PM Yield Loss (%) — raw material and packaging material losses against zero-base cost.

Improved first-pass yield, CpK/PpK (process capability), and product-quality consistency.

Improved inventory turns, safety-stock optimisation, and supplier-quality performance.

Number of production-deployed AI/ML solutions, adoption rate, model reliability, and quantified business value ($ impact to Conversion P&L; and ISC cost).

Within Country Relocation support available and for candidates voluntarily moving internationally some minimal support is offered through our Volunteer International Transfer Policy

Business Unit Summary

That means delivering a broad range of delicious, high-quality snacks that nourish life's moments, made with sustainable ingredients and packaging that consumers can feel valuable about.

We have a rich portfolio of strong brands globally and locally including many household names such as Oreo , belVita and LU biscuits; Cadbury Dairy Milk , Milka and Toblerone chocolate; Sour Patch Kids candy and Trident gum. We are a diverse community that can make things happen—and happen fast.

Mondelēz International is an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, gender, sexual orientation or preference, gender identity, national origin, disability status, protected veteran status, or any other characteristic protected by law.

Data Science

Analytics & Data Science

📌 Homebased Data Scientist (India)
🏢 Mondelēz International
📍 India