This job is with Pfizer, an inclusive employer and a member of myGwork – the largest global platform for the LGBTQ+ business community.

The Data

Scientist role will be part of the Supply Planning Data Intelligence organization and will be responsible for building, training, deploying, and maintaining AI/ML models and automation tools for supply chain master data. Acting as part of the "tech engine" of the Intelligent Data Factory initiative, this role develops advanced analytics solutions-such as optimization algorithms, predictive models, generative AI tools, and intelligent data agents-to drive autonomous and self-healing data pipelines.

The Data

Scientist works globally across multiple functions to enable a data-driven and automated supply chain, progressing through a phased delivery model that starts with foundational quick wins and evolves into a mature ecosystem of self-learning, autonomous data agents.

Develop Optimization & Simulation Algorithms: Design, build, and refine algorithms for supply chain planning optimization and scenario simulation. This includes creating AI models that optimize planning parameters (e.g., safety stock levels, lot sizes) and simulating planning decisions under various scenarios. Collaborate closely with Data Owners and supply chain subject matter experts to ensure that real-world constraints and business rules are accurately modeled.

Build Predictive Machine Learning Models: Develop and deploy predictive models using supervised and unsupervised machine learning techniques to improve master data-driven decision making. Examples include predicting key master data inputs (such as transit lead times or shelf-life constraints), implementing anomaly detection systems for data quality, and clustering techniques for pattern recognition. Maintain end-to-end data pipelines, ensuring models are regularly retrained and validated with clean, well-labeled data.

Create and integrate generative AI and natural language processing solutions to automate and enhance data management processes. Use large language models and related frameworks to auto-generate documentation or code (for data pipelines), suggest or populate master data values, and enable natural language interfaces (chatbot or Q&A; tools) that allow users to query and interact with data assets more intuitively.

Develop Intelligent Data Agents & Automation Bots: Design and deploy AI agents and robotic process automation (RPA) bots to handle repetitive master data tasks and proactively resolve data issues. Build bots that can automatically create, validate, or cleanse master data records. Engineer autonomous AI agents that monitor real-time data signals and trigger actions or alerts (for example, identifying inconsistencies and initiating corrections)



to keep master data accurate and up-to-date.

Integrate these agents with supply chain planning systems (e.g., Kinaxis) to close the feedback loop and ensure that planning adjustments are executed based on the latest data insights. End-to-End Model Deployment & Maintenance: Own the full lifecycle of data science solutions from development to deployment and ongoing maintenance. Ensure that all AI/ML solutions are deployed in the appropriate production environment and operate with high reliability and performance.

Monitor model and system performance, troubleshoot issues, and implement improvements or retraining as needed to maintain accuracy and efficiency. Establish self-healing mechanisms in data pipelines, so that the system can automatically address or alert on anomalies without manual intervention. Contribute to the continuous innovation of the Intelligent Data Factory by staying abreast of cutting-edge AI techniques and identifying opportunities to enhance automation.

Support a phased delivery approach to AI enablement in master data management: in Phase 1, focus on delivering foundational machine learning models and basic RPA bots that yield quick wins; in Phase 3, assist in cultivating a fully mature ecosystem of self-learning, autonomous data agents that require minimal human intervention. This role is the main lead to hand over validated and tested solutions into production with the Digital/IT team, becoming the business owner of the deployed solutions.

Education & Experience: Bachelor's degree in Computer Science, Data Science, Engineering, Mathematics or a related field is required. OperationsResearch,Machine Learning) is highly preferred.Minimum of 5+ years of hands-on experience in data science, machine learning, or AI development, with a track record of deploying models or algorithms into production environments.

Experience within supply chain, operations, or a similar domain is a plus, especially if it includes exposure to planning systems or master data management.

Technical Skills: Proficiency in programming and data analysis using languages and tools such as Python (including libraries like scikit-learn, pandas, TensorFlow/PyTorch, etc.) Hands-on experience with agentic AI platforms, preferable Microsoft Azure AI Foundry and RPA tools to build automated workflows (UiPath, Power Automate).



Demonstrated ability to develop machine learning models (regression, classification, clustering) and implement predictive analytics solutions. Comfortable working with big data technologies and cloud-based data platforms; able to query and manipulate data in SQL and utilize cloud services for model deployment.

Analytical & Problem-Solving Abilities: Exceptional analytical thinking and problem-solving skills, with the ability to tackle complex problems that may involve incomplete or imperfect data. Adept at mathematical reasoning and able to apply statistical analysis to validate model performance and interpret outcomes.

Leadership Qualifications: The successful candidate will operate as a trusted leader within the Global Supply Chain organization, driving data‑driven solutions in environments where deep technical expertise is not always present. This role requires the ability to translate complex data concepts into clear, actionable insights, effectively engage business stakeholders, and guide teams through ambiguity. The leader will be responsible for capturing and understanding end‑to‑end business constraints, balancing analytical rigor with practical execution, and identifying solutions that are scalable and sustainable given real‑world limitations in data models, systems, and organizational readiness.

Demonstrated curiosity and drive to stay up-to-date with the latest advancements in AI/ML, automation, and data science.

Organizational & Project Skills: Ability to manage autonomously multiple initiatives and deadlines concurrently.

Experience with project management coordinating diverse cross functional general teams using Agile development practices in data science projects. Possesses a strong sense of ownership over deliverables, ensuring quality and reliability of the solutions provided. Minimal travel (up to 10%) may be required for team workshops, training sessions, or cross-site collaboration, depending on project needs.

Work Location Assignment: Hybrid #At Pfizer we are a patient centric company, guided by our four values: courage, joy, equity and excellence.

Digital Transformation Strategy

One bold way we are achieving our purpose is through our company wide digital transformation strategy. We are leading the way in adopting new data, modelling and automated solutions to further digitize and accelerate drug discovery and development with the aim of enhancing health outcomes and the patient experience. This is to be used solely for accommodation requests with respect to the accessibility of our website, online application process and/or interviewing.

Se valorarán las candidaturas que puedan aportar certificados oficiales de discapacidad.

📌 Sr Manager Data Scientist Supply Chain (Madrid)
🏢 Pfizer
📍 Madrid