Senior Data Scientist
Role details
Job location
Tech stack
Job description
As Senior Data Scientist for Logistics, you will take complete technical ownership of building robust, well-engineered, data-driven solutions to exactly these problems. You will drive the vision and execution of data science for your vertical-setting the technical strategy, raising the engineering bar, and directly guiding hard modeling and architectural decisions. Your remit is both deep and broad: you will personally translate our toughest logistics challenges into sophisticated modeling strategies, write clean, production-grade code, and deliver scalable solutions that directly move the metrics that matter. These are some of the key components to the position:
- Move beyond static business rules to engineer intelligent, automated systems capable of making high-stakes operational choices under intense real-time uncertainty.
- Take complete ownership of the algorithmic policies governing critical logistics inflection points, specifically optimizing order preparation triggers and courier dispatch timing.
- Develop machine learning and optimization frameworks designed to mathematically balance conflicting business metrics (e.g., minimizing courier idle time vs. preventing order quality degradation).
- Build models that account for cause-and-effect relationships, allowing the platform to identify and adjust for non-compliant partner behaviors and system feedback loops.
- Construct robust, scenario-based simulation engines to stress-test hypotheses and validate algorithmic performance under volatile conditions before production deployment.
- Drive the entire project pipeline from initial conceptualization and mathematical modeling to live production deployment and continuous A/B experimentation.
- Partner closely with Machine Learning and Software Engineers to safely integrate complex, CPU-bound models into our real-time production logistics stack.
Requirements
- Advanced proficiency in machine learning methodologies, with extensive experience deploying and managing the full lifecycle of models in production.
- Proven experience solving Sequential Decision Making problems in domains such as capacity management, dynamic pricing, inventory control, robotics, recommendation systems, or a wider domain
- Deep proficiency in at least one of the following areas, alongside a solid conceptual understanding of the others: Markov Decision Processes, Stochastic Optimization, Reinforcement Learning, or Causal Inference.
- Strong Python skills for production-grade code, proficiency in SQL, and solid software best practices (testing, git, code reviews). Experience with feature computation pipelines like Apache Flink is a plus.
- Ability to intuitively understand feedback loops and inter-domain effects in complex networks. You prioritize simple, scalable, and effective solutions for complex projects.
- Strong leadership skills to guide, mentor, and develop junior data scientists. You excel at fostering team collaboration and a supportive engineering culture.
- A holistic approach to project management that bridges operational needs with technical execution. You confidently manage data science solutions from ideation through the full model lifecycle.
- Ability to generate innovative ideas and test hypotheses rigorously. You critically analyse approaches, assumptions, and business impact to refine strategies for optimal results.
- Strong expertise working within Agile environments to deliver results. You collaborate seamlessly across diverse, cross-functional teams.
- Excellent communication skills to translate complex data insights and data science concepts clearly. You can effectively present and tailor your message to both technical and non-technical stakeholders.