Data Scientist (Operations Research & ML)

Founded in 2018, MaxAB is a rapidly growing food and grocery B2B e-commerce and distribution platform that serves a network of traditional retailers (mom-and-pop stores) across the MENA region. Using proprietary technology, MaxAB offers a transformative pull-driven supply chain and a tech-product that empowers both traditional retailers and suppliers. MaxAB offers traditional retailers the simplicity of dealing with one supplier, transparent pricing, on-demand delivery, and a range of value-added and embedded finance solutions. Suppliers benefit from MaxAB's end-to-end supply chain solutions and business intelligence tools that allow them to accurately predict, monitor, and control the impact of their strategies in real time.

Our MaxAB talent are dedicated to uphold the MaxAB culture and values all while continuing to grow and improve services for our clients. They are innovating new ways to help improve the quality of life of the Egyptian retailer and soon to other retailers globally.

If you are passionate about working hard to make an impact and innovate new solutions, MaxAB is looking for top talent.

Role Overview

We seek a Data Scientist (Operations Research & ML) to develop optimization models and machine learning solutions for logistics, purchasing, and warehouse operations. The ideal candidate will have a strong foundation in mathematics, optimization, and machine learning and practical experience in solving real-world business problems.

This role is highly cross-functional, requiring collaboration with engineering, supply chain, finance, and operations teams to implement data-driven decision-making frameworks at scale.

 Key Responsibilities

• Operations Research & Optimization

- Design and implement last-mile and middle-mile delivery optimization models to reduce costs and improve efficiency.

- Develop algorithms for purchasing cycle optimization, balancing supplier constraints, warehouse capacity, and financial constraints.

- Optimize warehouse operations, space utilization, and picking strategies.

• Machine Learning & Predictive Modeling

- Build and deploy demand forecasting models to predict sales trends, optimize inventory, and improve fulfillment rates.

- Implement clustering and segmentation models to enhance supply chain decision-making and customer insights.

- Develop predictive models to improve logistics efficiency and operational planning.

• Scalability & Deployment

- Work closely with engineering teams to integrate ML and optimization models into production systems.

• Research & Continuous Improvement

- Stay up to date with the latest optimization and machine learning techniques to enhance model performance.

- Experiment with cutting-edge approaches in operations research, deep learning, and AI-driven optimization.

- Monitor deployed models and refine them based on real-world performance and business feedback.

• Collaboration & Business Impact

- Partner with stakeholders from logistics, supply chain, and finance to translate business problems into data-driven solutions.

- Present findings and recommendations to both technical and non-technical audiences.

 Qualifications & Experience

•  Education:

 - Master’s degree in Mathematics, Operations Research, Industrial Engineering, Computer Science, or a related field.

• Experience:

- Hands-on experience in logistics, supply chain optimization, and machine learning applications.

- Prior experience in e-commerce, fintech, or a fast-paced data-driven environment is a plus.

•  Technical Skills:

- Operations Research: Expertise in optimization techniques (linear programming, integer programming, heuristics).

- Machine Learning: Proficiency in supervised, unsupervised learning, and time series forecasting.

- Programming: Strong skills in Python (preferred) or R, with experience using Scikit-learn, TensorFlow, PyTorch, PuLP, Gurobi, or Pyomo.

- Data Handling: Experience working with SQL, Pandas, NumPy, and data visualization tools like Matplotlib, Seaborn, or Tableau.

- Deployment: Familiarity with MLOps, cloud platforms (AWS, GCP, or Azure), and API integrations is a plus.