About the Role
You'll join a small, senior Data Science team tackling one of the hardest forecasting problems in retail: fresh produce ordering. Every decision is a daily tradeoff between waste and availability, with immediate, visible impact in live stores — this is production ML with real operational consequences.
What You'll Do
-
Develop and improve distributional forecasting models, working across architecture, calibration, and coverage.
-
Monitor forecast quality metrics consistently and act swiftly when performance degrades.
-
Contribute meaningfully to inventory simulation and ordering policy frameworks, driving improvements through to production.
-
Shape technical direction in your focus area, contributing to methodology decisions and upholding high standards for code quality and production readiness.
-
Own end-to-end pipeline quality, from input data integrity through forecast output to live order recommendation performance.
-
Conduct ongoing monitoring and regular backtesting evaluations to assess model impact before issues reach stores.
-
Ship production-quality, well-tested, readable code with thorough review.
-
Leverage agentic AI tooling to work efficiently without compromising on craft.
-
Collaborate with Customer Success and Engineering to translate store-level findings into product improvements.
What We're Looking For
-
5+ years building systems that make decisions under uncertainty with real operational consequences — not research prototypes.
-
MSc or PhD in a quantitative field (Statistics, Mathematics, Physics, Operations Research, Computer Science, or similar).
-
Background in probabilistic forecasting, stochastic inventory simulation, or operations research, with solid working knowledge across all three.
-
Deep familiarity with distributional and probabilistic forecasting methods: quantile regression, LGBM with distributional output, GAMLSS-type models, conformal prediction.
-
Solid grounding in stochastic inventory theory, newsvendor models, and service level optimisation.
-
Production-grade Python and SQL on large, messy, real-world datasets.
-
Experience with ML model evaluation, monitoring, and backtesting in production environments.
-
Comfortable with GCP (BigQuery, Cloud Run, Vertex AI), dbt, and workflow orchestration (Cloud Composer, Airflow).
-
Strong software engineering practices: Git, containerisation, CI/CD.
-
Daily fluency with agentic AI coding tools (e.g. Claude Code, Cursor, or similar).
-
Fluent in English; German or French is a strong plus.
-
Domain knowledge in supply chain optimisation, demand planning, or perishables/grocery retail is a valuable plus.
-
Prior startup or scale-up experience is a plus.
Compensation & Benefits
-
Salary: €70,000 – €110,000 annually
-
Visa sponsorship: available
Location
Hybrid — Berlin, Germany. Relocation support to Berlin is available.