Lead Data Scientist

About the role

A highly experienced Lead Data Scientist is sought to define and drive the data science strategy across predictive analytics, promotion simulation, consumer trend modeling and computer vision. The role leads the design, development and deployment of advanced AI and machine learning solutions that support data-driven decisions in marketing, sales and innovation, balancing strategic direction with technical depth.

Key responsibilities

• Define and oversee modeling frameworks for forecasting, consumer analytics and computer vision.
• Translate complex business challenges into scalable data science solutions.
• Build, validate and optimize predictive and simulation models for demand forecasting and promotion impact.
• Lead the design of AI-based applications such as image recognition, trend detection and innovation analytics.
• Ensure strong MLOps, model governance and data quality practices.
• Partner with stakeholders across marketing, technology and operations to integrate models into business workflows.
• Mentor junior data scientists and establish best practices aligned with business goals.

Required profile

• 8-12 years of experience in data science, including leadership or mentoring responsibilities.
• Experience in predictive analytics, consumer insights or computer vision projects.
• Exposure to marketing mix modeling, A/B testing and campaign optimization.
• Familiarity with cloud data ecosystems (Azure, AWS, GCP) and CI/CD for ML pipelines.
• Proven ability to deliver end-to-end AI projects in complex environments, with strong communication and stakeholder management.

Required skills

• Machine learning and AI: regression, classification, clustering, NLP and computer vision.
• Predictive modeling: forecasting, time-series (ARIMA, Prophet, LSTM) and causal inference.
• Promotion and consumer analytics simulation models for pricing, promotions and ROI.
• Computer vision tools such as OpenCV, YOLO or Detectron2.
• Coding in Python/R and SQL; ML frameworks TensorFlow, PyTorch, Scikit-learn.
• MLOps and deployment on Azure ML, Databricks or AWS SageMaker.
• Data visualization with Power BI or Tableau.