Staff Data Scientist (Forecasting)

Join Source, a company focused on revolutionizing agriculture through data science and technology. As a Staff Data Scientist, you will be responsible for improving the accuracy of harvest forecasts and addressing various challenges in the agricultural forecasting system. This is a senior individual contributor role based in Amsterdam, where you will work closely with data scientists, crop scientists, and growers. You will have the opportunity to make a significant impact on the agricultural industry and contribute to sustainable food production.

Collaborer avec les scientifiques des données, les scientifiques des cultures et les cultivateurs pour améliorer continuellement les prévisions et les modèles, en partageant vos connaissances et votre expertise.

Around 10 years of hands-on modelling or forecasting, with models of physical or real-world systems that ran in production for more than one season. Energy, weather, process industry, plant breeding, pharma, batteries or trading: the field matters less than the fact that it was real

At Source, we value diversity of background and perspective. People assess their own qualifications differently, so please apply even if you do not tick every box. We are looking for the right person, not a perfect CV

About Source.ag

Deep expertise in time series and probabilistic forecasting: Bayesian and hierarchical models, gradient boosting, deep learning for sequences, and uncertainty quantification on small, irregular datasets

Responsibilities

• Assumer la responsabilité de l'exactitude des prévisions de récolte pour les tomates, les poivrons et les concombres, en identifiant et en résolvant les problèmes liés aux données d'entrée, à l'échantillonnage des plantes ou aux plans des cultivateurs.
• Concevoir et construire des modèles hybrides qui combinent la physiologie des cultures et le climat des serres avec des méthodes statistiques et d'apprentissage automatique, et mettre en place un système d'évaluation robuste.
• You have shipped models that broke when the world changed (a new season, a new site, a new customer) and fixed them, more than once. You can tell us what broke each time
• Production-grade Python (pandas or polars, scikit-learn, PyTorch or JAX, PyMC or similar) and solid engineering habits (Git, testing, CI/CD, Databricks, AWS), so your models run in production without you
• Validation that holds up: backtests against strong baselines, error analysis tied to business impact, drift monitoring, and evaluation tools other people kept using after you built them
• You work AI-native: coding agents and LLM tools are how you work every day, and you know where they fail

Requirements

Clear communication with growers, product and engineering alike

• An MSc or PhD background and the habit of reasoning from first principles
• You have worked next to people with a higher standard than yours, and can say what they taught you
• You have taken a forecast people did not trust and made it one a business commits money on
• Physics-informed ML, mechanistic or process-based models, data assimilation (for example Kalman filtering) or system identification
• Publications, talks or open-source work on forecasting or scientific ML

Preferred

• A degree in engineering, physics, applied mathematics, statistics or econometrics

Pay

EUR 107,000 - 120,000