Data Scientist

Role Overview

The Data Scientist will be responsible for designing, developing, and implementing sophisticated AI and Machine Learning solutions to enhance efficiency in express distribution networks, including activities such as route optimization, demand prediction, and automated parcel sorting. The role serves as a bridge between theoretical data concepts and practical operational improvements aimed at delivering measurable business value.

Key Responsibilities and Performance Metrics

• Achieve defined model performance targets, including metrics like MAPE for forecasting and F1-score for classification, aligned with 2026 operational criteria.
• Deliver quantifiable business benefits, such as reducing costs per kilogram or improving last-mile delivery success percentages.
• Shorten time from idea conception to deploying scalable, reliable AI models in production environments.
• Maintain high uptime and consistent performance of AI systems with minimal drift over time.
• Gather and incorporate feedback from stakeholders to ensure the clarity and usefulness of analytic insights and solutions.

Preferred Qualifications

• Certifications related to cloud machine learning platforms (for example, AWS Certified Data Research or Google Professional ML Engineer).

Experience Requirements

• At least 5 years of overall experience in Data Science or Analytics fields.
• Minimum 4 years of practical experience in developing and deploying machine learning models in production environments.
• Industry experience particularly in logistics, supply chain, e-commerce, or express distribution is highly desirable.
• Proven success leading 2 to 3 significant AI projects from initiation to results demonstrating business impact.

Technical and Functional Expertise

• High proficiency in Python or R programming and familiarity with machine learning libraries including TensorFlow, PyTorch, Scikit-learn, and XGBoost.
• Strong knowledge in advanced analytics domains such as deep learning, natural language processing, and reinforcement learning, especially applied to logistics routing problems.
• Hands-on experience with SQL and big data ecosystems like Spark and Hadoop, alongside cloud ML platforms such as AWS SageMaker, Azure ML, or Google Vertex AI.
• Solid competency in machine learning operations covering model versioning using MLflow, container technologies like Docker/Kubernetes, and implementation of CI/CD workflows.
• Experience in optimization techniques, including linear programming and combinatorial optimization, applicable to supply chain and logistics challenges.

Eligibility

Applicants with any graduate degree are eligible to apply for this position.