Senior Data Scientist

Overview

We are looking for a Senior Data Scientist based in Berlin who is passionate about addressing large-scale logistics challenges using advanced techniques in machine learning, optimization, reinforcement learning, and causal inference. This role involves leading the creation, implementation, and continuous refinement of intelligent decision-making systems critical to logistics operations, managing the end-to-end data science strategy for logistics optimization, and translating complex operational issues into scalable AI-driven solutions.

Primary Responsibilities

• Create data-driven decision engines that replace static operational rules.
• Build automated frameworks for real-time decision-making under uncertainty.
• Improve logistics processes including order preparation timing, courier dispatch, capacity allocation, resource scheduling, and delivery optimization.
• Develop and deploy machine learning models with techniques such as predictive modeling, reinforcement learning, stochastic optimization, causal inference, and Markov decision processes.
• Continuously enhance models to adapt to evolving business conditions through experimentation.
• Tackle multi-objective optimization problems balancing delivery speed, cost efficiency, courier utilization, customer wait times, operational efficacy, and service quality.
• Design mathematical optimization frameworks and scalable decision engines for real-time logistics operations.
• Build causal models to capture cause-effect dynamics within operations, uncover feedback loops, behavioral trends, inefficiencies, and non-compliant partner activities, enhancing decision quality through causal analysis.
• Develop simulation platforms for testing operational strategies against various scenarios including demand volatility, capacity constraints, disruptions, and network changes to reduce risk prior to deployment.
• Lead projects from problem definition through data exploration, model design, experimentation, deployment, monitoring, and optimization ensuring production readiness.
• Design and conduct controlled experiments and A/B tests to measure impact and drive data-driven decisions.
• Write clean, scalable Python code and collaborate with engineers to integrate models into real-time systems while adhering to software engineering best practices like testing, version control, code reviews, documentation, and CI/CD pipelines.
• Provide technical leadership and mentorship to junior data scientists, define standards, review methodologies, and foster a culture of innovation and continuous learning.
• Collaborate cross-functionally with machine learning engineers, software engineers, product managers, operations teams, and business leaders to translate business needs into analytical solutions aligned with organizational goals.

Experience and Qualifications

• Significant experience deploying machine learning models in production environments.
• Proven track record in solving sequential decision-making challenges.
• Experience in sectors such as logistics, supply chain, dynamic pricing, capacity management, inventory optimization, recommendation systems, transportation networks, or robotics.

Technical Expertise

• Machine Learning & AI: production ML, predictive modeling, feature engineering, model serving, experimentation platforms, lifecycle management.
• Optimization & Decision Science: reinforcement learning, stochastic optimization, MDPs, dynamic decision systems, operations research, mathematical optimization.
• Causal Analytics: causal inference, impact assessment, counterfactual models, feedback loop & behavioral analysis.
• Simulation & Modeling: scenario analysis, Monte Carlo, discrete event simulation, digital twins, stress testing.
• Programming: advanced Python and SQL skills.
• Data Engineering: feature engineering pipelines, Apache Flink preferred, model deployment platforms, distributed data processing.
• Software Engineering: proficiency with Git, unit testing, CI/CD, code reviews, design patterns, and production monitoring.