Data Scientist

About the Role

You will join the AkzoNobel's Advanced Analytics team, working at the heart of a global manufacturing environment. Your mission is to accelerate world-class end-to-end supply chain performance by delivering scalable, secure, and high-impact AI/data products on our Azure cloud platform. You will collaborate with supply chain leaders (MAKE, SOURCE, DELIVER, QUALITY, PLAN, IBP), IT, engineering, and external software partners. You will operate with a product mindset, turning business needs into AI-enabled capabilities that are reliable in production, measurable in value, and continuously improved.

Job Purpose

On a global scale, you will co-deliver AI and analytics solutions that improve service, cost, inventory, and planning stability, including:

• E2E Reporting & Decision Intelligence: Modern analytics and KPI frameworks across Integrated Supply Chain (MAKE, SOURCE, DELIVER, QUALITY, PLAN & IBP), enabling faster and better decisions.
• Master Data Quality & Automation: Improve and govern master data (lifecycle statuses, MRP parameters, routings, capacity, production data capture) to stabilize planning and execution.
• Predictive, Prescriptive & Optimization Models: Build and deploy models on big-data platforms to optimize MRP and network design, such as demand segmentation (ABC/XYZ), supply policies (MTO/MTS), lot sizing, safety stock placement/levels, and capacity-aware planning.
• Automation for IBP & Financial Planning: Deliver robust, auditable and scalable global solutions for planning processes with a strong focus on automation, reliability, adoption, and sustainable performance.
• AI Enablement & Responsible AI: Introduce and scale AI capabilities (ML, optimization, and GenAI where valuable) with clear governance, model risk management, and ethical/secure implementation.

Role & Responsibilities

You will contribute as Data Scientist + AI Product Owner in an Agile/DevOps setup.

• Data Science & Applied AI

• Design, train, evaluate, and deploy machine learning, statistical, and optimization solutions for forecasting, segmentation, anomaly detection, root cause analysis, and decision recommendations.

• Apply best practices for feature engineering, model validation, uncertainty quantification, and error metrics aligned with supply chain decisions.

• Translate business questions into testable hypotheses and measurable model outcomes (e.g., service level impact, inventory reduction, stability improvements).

• AI Product Ownership (end-to-end)

• Define product vision, value proposition, roadmap, and success metrics for AI/data products.

• Manage and prioritize the backlog (epics/user stories), align stakeholders, and drive iterative delivery.

• Ensure adoption: design for user workflows, change management, and training materials.

• Drive continuous improvement based on feedback, performance monitoring, and business results.

• Data Engineering & Platform Collaboration

• Work hands-on with data pipelines: extract, cleanse, standardize, validate and document data.

• Partner closely with Data Engineers/Architects to build robust data products (quality checks, lineage, access controls, reusability).

• Contribute to scalable patterns for batch/stream processing (where relevant) within Azure.

• MLOps / LLMOps / Production Reliability

• Operationalize models with CI/CD, automated testing, monitoring, and drift detection.

• Establish model lifecycle practices: versioning, retraining triggers, model registry, and reproducible pipelines.

• For GenAI use cases: implement skills/prompt/version management, evaluation, guardrails, and secure integration (e.g., retrieval-augmented generation for supply chain knowledge).

• Data Analytics, Reporting & Storytelling

• Build decision-grade dashboards and semantic layers for multi-stakeholder reporting (Power BI or similar).

• Communicate findings clearly to business and technical audiences; create functional/technical documentation.

• Governance, Security & Responsible AI

• Ensure solutions comply with data privacy, security standards, and Responsible AI principles (fairness, explainability, traceability, auditability).

• Define and track model KPIs (accuracy, stability, bias checks, latency, uptime, business outcome metrics).

Requirements & Tech Stack

• Data Science & ML Concepts
• Statistical libraries
• Python
• SQL
• Deployments
• Azure
• Descriptive & Prescriptive Analytics
• Datalake & Synapse
• Pyspark
• Creating Notebooks (Python & SQL)
• Databricks Dashboarding
• DBK Genie
• MLOps / LLMOps
• Power BI (or similar for reporting)

Qualifications

• Specific roles may have overlapping or more specialized skill requirements.