🇩🇪 Berlin, Germany · 15h ago
Senior Data Scientist
SoTalent
LinkedInseniorEnglish-friendly
Senior Data Scientist📍 Location: Berlin, Berlin, Germany🏢 Industry:Food and Beverage Services💼 Work Setting: HybridAre you passionate about solving large-scale logistics problems using machine learning, optimization, reinforcement learning, and causal inference?We are seeking a Senior Data Scientist to lead the design, development, deployment, and continuous improvement of intelligent decision-making systems that power critical logistics operations. This role owns the end-to-end data science strategy for logistics optimization, transforming complex operational challenges into scalable, production-grade AI and optimization solutions.The ideal candidate combines deep expertise in machine learning, sequential decision-making, optimization, simulation, experimentation, and software engineering while providing technical leadership across cross-functional teams.Key ResponsibilitiesLogistics Decision IntelligenceDesign intelligent systems that replace static operational rules with data-driven decision engines.Build automated decision-making frameworks capable of operating under real-time uncertainty.Optimize critical logistics operations including:Order Preparation TimingCourier Dispatch DecisionsCapacity AllocationResource SchedulingDelivery OptimizationDevelop solutions that directly improve operational efficiency and customer experience.Machine Learning & Advanced AnalyticsDesign, train, deploy, and monitor production-grade machine learning models.Apply advanced methodologies including:Predictive ModelingReinforcement LearningStochastic OptimizationCausal InferenceMarkov Decision Processes (MDPs)Build models that adapt dynamically to changing business conditions.Continuously improve model performance through experimentation and optimization.Sequential Decision-Making & OptimizationDevelop algorithmic policies for high-impact operational decisions.Solve complex optimization challenges involving competing objectives such as:Delivery Speed vs. Cost EfficiencyCourier Utilization vs. Customer Wait TimeOperational Efficiency vs. Service QualityDesign mathematical optimization frameworks that support real-time decision-making.Implement scalable decision engines for logistics operations.Causal Modeling & System DynamicsBuild models that understand cause-and-effect relationships within operational systems.Identify:Feedback LoopsBehavioral PatternsSystem InefficienciesNon-Compliant Partner ActivitiesDevelop mechanisms that account for downstream operational impacts.Improve decision quality through causal reasoning and impact analysis.Simulation & Scenario TestingDesign simulation platforms to evaluate operational strategies before deployment.Build scenario-based testing environments that model:Demand VolatilityCapacity ConstraintsOperational DisruptionsNetwork DynamicsValidate algorithm performance under varying business conditions.Reduce production risk through robust simulation and testing.End-to-End Model OwnershipLead projects through the entire lifecycle:Problem DefinitionData ExplorationModel DesignExperimentationDeploymentMonitoringOptimizationEnsure production-readiness of all analytical solutions.Establish operational metrics and monitoring standards.Experimentation & A/B TestingDesign and execute controlled experiments.Measure business impact through statistical analysis.Evaluate competing models and strategies.Drive data-informed decision-making using rigorous experimentation frameworks.Continuously refine operational policies based on experimental results.Software Engineering & Production DeploymentDevelop clean, scalable, production-quality Python code.Collaborate with engineers to integrate models into real-time systems.Apply software engineering best practices including:TestingVersion ControlCode ReviewsDocumentationCI/CD WorkflowsEnsure models are performant, reliable, and maintainable.Technical Leadership & MentorshipDefine data science standards and technical direction for logistics initiatives.Mentor junior data scientists and provide technical guidance.Review model designs, analytical approaches, and implementation strategies.Promote engineering excellence and strong analytical practices.Foster a culture of innovation and continuous learning.Cross-Functional CollaborationPartner closely with:Machine Learning EngineersSoftware EngineersProduct ManagersOperations TeamsBusiness LeadersTranslate business problems into analytical solutions.Communicate technical approaches clearly to stakeholders.Align data science initiatives with organizational objectives.QualificationsRequired ExperienceExtensive experience developing and deploying machine learning models in production environments.Proven success solving sequential decision-making problems.Experience working in domains such as:LogisticsSupply ChainDynamic PricingCapacity ManagementInventory OptimizationRecommendation SystemsTransportation NetworksRoboticsAdvanced Technical ExpertiseMachine Learning & AIProduction Machine LearningPredictive ModelingFeature EngineeringModel ServingExperimentation PlatformsModel Lifecycle ManagementOptimization & Decision ScienceReinforcement LearningStochastic OptimizationMarkov Decision Processes (MDPs)Dynamic Decision SystemsOperations ResearchMathematical OptimizationCausal AnalyticsCausal InferenceImpact AnalysisCounterfactual ModelingFeedback Loop AnalysisBehavioral ModelingSimulation & ModelingScenario AnalysisMonte Carlo SimulationDiscrete Event SimulationDigital TwinsStress Testing FrameworksTechnical SkillsProgrammingPython (Advanced)SQL (Advanced)Data Engineering & PlatformsFeature Engineering PipelinesApache Flink (Preferred)Model Deployment PlatformsDistributed Data ProcessingSoftware EngineeringGitUnit TestingCI/CDCode ReviewsDesign PatternsProduction MonitoringSourced from LinkedIn. Relocantly aggregates public job postings; apply on the original site.