Job Description:
About the Role
Kaleris is seeking an experienced Senior Data Scientist to lead the design and delivery of machine learning and reinforcement learning solutions across our logistics and supply chain products. You will own end-to-end modeling initiatives—from problem framing and data strategy through validation and production operations—leveraging AI tooling to drive measurable business outcomes.
Responsibilities
- Lead end-to-end ML solution design, translating business objectives into modeling plans, success metrics, and deployment strategies.
- Architect training and evaluation environments, including simulators, to safely assess model behavior prior to live deployment.
- Establish data quality standards and build reliable pipelines for ingestion, cleaning, feature engineering, labeling, and experiment tracking.
- Define rewards, constraints, and safety considerations; plan offline evaluations and controlled experiments to validate performance.
- Validate and operate production models: define acceptance criteria and test plans, continuously monitor performance/latency/drift, investigate anomalies, and apply corrective measures in partnership with software engineering.
- Drive responsible AI practices, model governance, documentation standards, and reproducible experimentation throughout the ML lifecycle.
- Partner with product and engineering to scope initiatives, prioritize roadmaps, and integrate models into scalable services with robust observability.
- Mentor and coach data scientists; lead technical reviews, elevate code quality, and promote best practices.
- Communicate findings and recommendations to stakeholders and leadership through clear narratives and visualizations; influence decision-making with data.
Requirements
- Master’s in a quantitative field (Computer Science, Statistics, Mathematics, Operations Research, Engineering) or equivalent experience. PhD is a plus.
- 6+ years of professional experience in data science/ML, including delivering models to production and measuring business impact.
- Deep knowledge of statistics, data modeling, machine learning, and visualization; practical experience applying reinforcement learning concepts to real-world decision-making.
- Strong proficiency in Python and a deep learning framework (PyTorch or TensorFlow); solid SQL and data wrangling skills.
- Proven experience with experiment design, hypothesis testing, and model diagnostics; ability to build clear, decision-focused visualizations.
- MLOps competence: containers, CI/CD, and deploying models in cloud environments (Azure/AWS/GCP).
- Track record of operating production ML systems, including monitoring, alerting, and incident response.
- Excellent communication, stakeholder management, and the ability to lead cross-functional initiatives with global/distributed teams.
Preferred
- Simulation experience (discrete-event or agent-based) and familiarity with queueing and stochastic modeling.
- Logistics and supply-chain domain knowledge (terminal operations, yard management, transportation networks, inventory flows).
- Background in optimization and decision intelligence for complex, noisy, or partially observable environments.
- Experience with model versioning, monitoring, and automated retraining.
Why Join Kaleris?
- Competitive salary and comprehensive benefits.
- Inclusive, diverse, and collaborative team culture.
- The opportunity to lead AI initiatives at the frontier of decision intelligence for the supply chain.
- Significant impact on real-world operations, with room to grow domain expertise and technical scope.
Kaleris is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.
Top Skills
What We Do
Kaleris is a leading provider of cloud-based supply chain execution and visibility technology solutions. Many of the world's largest brands rely on Kaleris to provide mission-critical technology for yard management, transportation management, maintenance and repair operations, terminal operating systems, and ocean carrier and vessel solutions. By consolidating supply chain execution software assets across major nodes and modes, we address the dark spots and data gaps that cause friction and inefficiency in the global supply chain.
