Data Scientist

Responsibilities:

• Design, develop, implement, and maintain data science and machine learning solutions to meet enterprise goals.
• Collaborate with cross-functional teams to leverage statistical modeling, machine learning, and data mining techniques to improve forecast accuracy and aid strategic decision-making across the organization.
• Scale the proven AI-ML product across the SAPMENA region.
• Deep understanding of business/functional needs, problem statements, and objectives/success criteria.
• Develop and maintain sophisticated statistical forecasting models, incorporating factors such as seasonality, promotions, media, traffic, and other economic indicators.
• Collaborate with internal and external stakeholders, including business, data scientists, and the product team, to understand the business and product needs and translate them into actionable data-driven solutions.
• Review MVP implementations, provide recommendations, and ensure data science best practices and guidelines are followed.
• Evaluate and compare the performance of different forecasting models, recommending optimal approaches for various business scenarios.
• Analyze large and complex datasets to identify patterns, insights, and potential risks and opportunities.
• Communicate forecasting results and insights to both technical and non-technical audiences through clear visualizations and presentations.
• Stay up to date with the latest advancements in forecasting techniques and technologies, continuously seeking opportunities for improvement.
• Contribute to the development of a robust data infrastructure for AI-ML solutions, ensuring data quality and accessibility.
• Collaborate with other data scientists and engineers to build and deploy scalable AI-ML solutions.

Requirements:

• 5+ years in developing and implementing forecasting models.
• Proven track record in data analysis (EDA, profiling, sampling), data engineering (wrangling, storage, pipelines, orchestration).
• Proven expertise in time series analysis, regression analysis, and other statistical modelling techniques.
• Experience in ML algorithms such as ARIMA, Prophet, Random Forests, and gradient boosting algorithms (XGBoost, LightGBM, and CatBoost).
• Experience in model explainability with Shapley plots and data drift detection metrics.
• Strong programming and analysis skills with Python and SQL, including experience with relevant forecasting packages.
• Prior experience in data science and ML engineering on Google Cloud.
• Proficiency in version control systems such as GitHub.
• Strong organizational capabilities and ability to work in a matrix/multidisciplinary team.
• Excellent communication and presentation skills, with the ability to explain complex technical concepts to a non-technical audience.
• Experience in beauty or the retail/FMCG industry is preferred.
• Experience in handling large volumes of data (> 100 GB).
• Experience in delivering AI-ML projects using Agile methodologies is preferred.
• Proven ability to work proactively and independently to address product requirements and design optimal solutions.

Skills

ARIMA, CatBoost, Demand Forecasting, Gradient Boosting, LightGBM, Prophet, Python, Random Forests, SQL, XGBoost