Energy is responsible for almost three quarters of worldwide greenhouse gas emissions. To reduce these emissions and fight climate change, more and more sectors of the economy are electrifying, and the production of this electricity is shifting towards wind and solar power. As this happens, power grids must maintain their key property of always perfectly balancing electricity supply and demand — an increasingly difficult task as more and more of the supply is influenced by the weather.
Dexter Energy is an Amsterdam-based startup that’s solving this problem using AI-based forecasting and optimization services for energy companies. Our software makes renewables more predictable and profitable, helping push fossil fuels out of the market, and speeding up the energy transition.
Following our recent Series A funding round, we are currently accelerating the growth of our company, and we are looking for an experienced MLOps Engineer to join our diverse team of curious, ambitious and highly-skilled people.
As part of our MLOps team, you are responsible for productionizing the — both classical and deep learning — machine learning models that forecast electricity production (by solar and wind parks) and consumption (by households and large-scale users). Our customers manage thousands of renewable assets, and optimize them every day using our Forecasting as a Service products. From day-ahead forecasting to intra-day nowcasting, you’ll be working on a diverse set of challenges, using technologies like Kubernetes, Python and its ML stack, Google Cloud Platform, BigQuery, and more. We care deeply about writing great software: our ML models and infrastructure are all implemented using the latest best practices in terms of reproducibility, availability, modularity, and automated testing.
Something about you
- You are excited to join a company that is working towards a cleaner energy future.
- You thrive in a collaborative, entrepreneurial environment and are motivated to keep learning new things.
- You care deeply about writing great software.
Read more below.
What you might be working on
- Serving ML models that forecast electricity production and consumption for short-term power markets.
- Designing, building and maintaining our MLOps infrastructure.
- Distributed infrastructure for training and model persistence.
- Model serving and inference.
- Dashboards showing (historical) performance.
- Data engineering
- Data ingestion from both internal and external sources.
- Data validation, feature engineering, and preprocessing pipelines.
- Integrating with customers to deliver our forecasts.
BSc Computer science or equivalent practical experience.
2+ years’ experience in a professional software engineering environment.
Experience setting up model serving pipelines.
Knowledge of and experience with the Python ML ecosystem.
- Experience with Google Cloud Platform.
- MSc or PhD Computer science.
Working at Dexter
- Work in a clean-tech scale-up that has an impact on the environment.
- Build a cool company in a highly motivated and entrepreneurial team.
- Make decisions quickly in a low hierarchy environment.
- Learn a lot of things in a short time, from colleagues who are excited to share their knowledge (about the energy industry or anything else).
- Get to work in a modern containerized microservices-based stack (python, k8s), with a well-tested codebase, standardized CI/CD pipelines, and passionately maintained documentation. We follow best practices to the bone and love to write great software!
- Collaborate within an ambitious team, which also values a healthy work-life balance. We encourage you to plan work around the hobbies that you want to pursue!
If you are interested in learning more about this position and what Dexter Energy Services can offer to you then please get in contact:
Jordan Cantlow, firstname.lastname@example.org / +31 855 607 326
Dexter is proud to be an equal opportunity workplace and is an affirmative action employer. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability or gender identity.