NEW Data & ML Engineer – eMobility (SaaS)

Deftpower

1d•Hybrid

About The Position

Deftpower is hiring a Data & ML Engineer for its Flexibility team, which aggregates EV charging sessions into flexibility for energy markets. The role focuses on building the data pipelines and prediction models that help make EV charging cheaper for drivers and support grid balancing. Predictions cover individual driver and charging-session behaviour, as well as the reliable flexibility that a pool of sessions can deliver to the market. You will build pipelines that transform raw charging and market data into model-ready datasets, maintain data quality, develop prediction models, and deploy improved models to production. You will collaborate with C#/.NET developers to integrate models into Deftpower’s platform and monitor them after launch. The team works in five-week Shape Up cycles, with freedom to decide how to meet each cycle’s goal and responsibility for the outcome. The position is based in Arnhem, with an average of two days per week in the office; fully remote work is not a fit for the role. The position offers a choice of 36 or 40 hours per week. Deftpower has more than 120 employees and works in English day to day.

Requirements

At least 3 years of experience building data pipelines on high-volume data.
Experience putting prediction models into production.
Rigorous approach to data, including testing assumptions and understanding how much a prediction can be trusted.
Python and its data and machine-learning stack.
SQL.
Experience deploying models to the cloud.
Git and pull-request workflows.
Curiosity about AI coding tools.
Ability to work in English every day.
Proactive approach, adaptability, and comfort with direct feedback and changing plans.

Nice To Haves

Dutch language skills.
Experience with probabilistic forecasting.
Azure and Bicep experience.
Experience in energy markets, EV charging, or battery optimisation.

Responsibilities

Design and build data pipelines that transform raw charging and market data into model-ready datasets.
Monitor data quality and identify issues before they affect models.
Develop prediction models and put them into production when they outperform the existing models.
Work with .NET developers to integrate models into the platform.
Monitor models after they are live.
Communicate insights from data as clear choices for technical and business colleagues.
Take initiative, investigate unanswered questions, and make work visible to colleagues.