Medior data scientist/engineer

Quintel; Amsterdam; Hybrid; EUR 42,000 - 58,000; Full time

Benefits offered by this job

Pension plan

25 holidays

Office Amsterdam canals

Partly remote option

Team events and training

Job summary

Quintel seeks a data engineer/scientist to design and own new data pipelines in the Modelling & Development team in Amsterdam. You’ll build scalable pipelines, ensure traceability of numbers, and replace parts only when justified.

You’ll work at the intersection of data engineering and data science, aligning data with standards. You’ll be part of an Amsterdam office that offers a pension plan, 25 holidays, and opportunities for training, with the option to work partly remote.

Qualifications

• 2 to 5 years of relevant experience in data engineering or data science.
• University degree in a relevant field.
• Experience with Python and Git, and ability to navigate complex data.

Responsibilities

• Design and build new data pipelines and establish ownership.
• Convert and integrate datasets into a reproducible, scalable pipeline.
• Develop checks to make anomalies visible and trace data provenance.
• Collaborate with team to align data with standards and requirements.
• Work in an environment that values initiative and clear communication.

Skills

Python

Git

Excel

Data engineering

Data science

Education

University degree in data science, energy science, econometrics, physics or engineering

Tools

GitHub

Job description

You’ll join Quintel’s Modelling & Development team. This team works on the calculations, data and software behind the ETM. The data ranges from technology specifications, costs, and hourly profiles to representations of the complete energy system of more than 400 regions (the European countries, every Dutch province and municipality) for a reference year, built up from public sources.

The way we process that data has grown organically and should be structurally improved. The path from source to calculations is not yet a streamlined process: we want to move to pipelines that are fully script-based and modular. We have the time and resources to do this over the next four years. The goal is for our way of processing energy data to become the standard for the energy transition in the Netherlands and Europe: from EU level down to a neighbourhood or industrial site.

What you will work on

You will design the new pipelines, build them and, in time, take ownership of them. We’re deliberately looking for someone at the intersection of data engineering and data science: you build the infrastructure and take ownership on the subject matter. You know not only how the data flows through the system, but also what the numbers mean and when they’re wrong. What you build has to be traceable: every number can be traced back to its source. The team also has to be able to keep working with it. You build on what’s already there and only replace it when there are good reasons to do so.

Examples of what you’ll work on:

• Designing and building a new pipeline for the national datasets, merging two existing routes and aligning the data with international standards such as the Eurostat energy balances;
• Converting the regional datasets (municipalities, RES regions and provinces), hourly profiles and local data from loose notebooks and Excel files into a single reproducible, scalable pipeline;
• Building checks that make anomalies visible, both for us and for our users;
• Bringing hourly profiles, costs and technology specifications, and local data into the same structure.

What we offer

• An inspiring, motivated team in which everyone takes initiative and speaks up;
• A salary between €3,800 and €5,200 per month depending on your experience, plus a pension plan and 25 holidays;
• The chance to build the data foundation for a model used by thousands of users in the Netherlands and Europe;
• Room to develop yourself in a growing company, with suitable training and coaching;
• Monthly drinks, an annual team weekend and strategy days;
• An office on the canals of Amsterdam, with good coffee and a (vegetarian and largely organic) lunch;
• The option to work partly remote (Monday is our fixed office day)

Who we’re looking for

We’re looking for a new colleague for 32 to 40 hours a week, based in our Amsterdam office. You:

• have 2 to 5 years of relevant experience as a data engineer / scientist or in a comparable role, and a university degree in a relevant field such as data science, energy science, econometrics, physics or engineering;
• work comfortably with Python and Git, and can find your way around a complex Excel file or a GitHub repository;
• work analytically and systematically, with an eye for detail: one wrong unit propagates through hundreds of datasets;
• are proactive: you don’t wait for a task to land on your desk, but keep an overview of what others are working on and where the dependencies lie;
• are pragmatic: you improve what’s already there, step by step, rather than starting over;
• want to get to know the energy system well enough to understand where the data needs of a modeller, consultant or client come from;
• can explain clearly what is going on, in both Dutch and English.
• Ideally, but not essential: knowledge of energy statistics (such as energy balances or the Klimaatmonitor), experience with tooling for data pipelines or data validation (such as Dagster or Airflow), and experience with publishing open data.

• Please note that we unfortunately cannot sponsor residence or work permits