Full Stack Data Scientist

HEINEKEN is seeking a talented and motivated Senior Data Scientist with a strong background in Full Stack. The role involves working on challenging business problems, requiring development of innovative optimization models, and deploying them in ways that deliver significant business value. The mission of Global Analytics is to lead HEINEKEN into becoming a data-driven company and the best-connected brewer. As a team, we radiate a data-driven entrepreneurial culture to the rest of the company.

We act as an incubator for smart data products in all business areas, from sales to logistics and marketing to purchasing. This approach has allowed us to grow rapidly and launch many value-creating use cases from the management of spare parts to the allocation of media spending.

Key Responsibilities

1. End-to-End Data Product Development

- Own the full lifecycle of data solutions, from ETL/ELT pipelines to ML model deployment and performance tracking.

- Translate ambiguous business requirements into actionable technical roadmaps and deliver scalable solutions.

- Drive projects independently while collaborating with Data Engineers, MLOps, and stakeholders.

2. Machine Learning & Advanced Analytics

- Build, validate, and deploy ML models (classification, regression, anomaly detection, clustering) using scikit-learn pipelines.

- Apply advanced techniques (e.g., Bayesian methods, time-series forecasting, optimization) where needed.

- Ensure robust model validation, drift detection, and performance monitoring.

3. Data Engineering & Cloud Infrastructure

- Design and optimize large-scale data pipelines (batch/streaming) using PySpark, Dask, or Kafka.

- Implement cost-efficient cloud solutions on AWS (SageMaker, Athena, S3, Glue) with CI/CD best practices.

- Write clean, maintainable, and testable Python code following OOP principles and unit testing standards.

4. Stakeholder Communication & Visualization

- Develop interactive dashboards (Streamlit, Plotly Dash, PowerBI) to communicate insights.

- Deliver clear, actionable reports (EDA, model performance, data quality) for technical and non-technical audiences.

5. Leadership & Best Practices

- Mentor junior team members and lead technical discussions on architecture and design.

- Advocate for agile methodologies, automation, and scalable data practices.

Core Qualifications Technical & Professional Requirements

- Education: MS/PhD in Computer Science, Statistics, AI, or related field.

- Experience: 8+ years in full-stack data science, covering data pipelines, ML, and deployment.

- Programming & ML: - Expert in Python (OOP, design patterns, unit testing).

- Proficient in scikit-learn, pandas, PySpark, SQL. - Experience with TensorFlow/PyTorch (nice-to-have).

- Cloud & DevOps:

- Hands-on with AWS (SageMaker, Athena, S3, Lambda).

- Familiarity with CI/CD, Docker, Kubernetes.

- Data & Analytics:

- Strong feature engineering, model validation, and drift detection skills.

- Experience with real-time data (Kafka, Spark Streaming).

-Soft Skill:

- Self-starter with ownership mindset and business-value focus.

- Excellent stakeholder management (written/verbal).

- Agile team experience with strong collaboration skills. Bonus Skills (Preferred but Not Required)

- Graph algorithms, causal inference, or clustering.

- IoT data modeling and deployment.

- Spark ML or MLOps experience.

Why Join Us?

✅ High Impact: Drive decisions with data products that directly influence business strategy.

✅ Modern Tech Stack: Work with cutting-edge tools (AWS, SageMaker, Spark, Kubernetes).

✅ Growth & Leadership: Mentor talent, shape best practices, and grow your technical leadership.

✅ Flexibility: Remote-friendly culture with competitive compensation.  ndra, Hadoop, Spark, Tableau)