Senior Machine Learning Engineer

Eneco; Rotterdam; On-site; EUR 90,000 - 140,000; Full time

Job summary

Eneco is seeking a Senior ML Engineer in Rotterdam to own production-ready ML pipelines and model deployment. You will collaborate with data scientists and data engineers to operationalize models for demand forecasting, pricing insights, and market simulations.

You will drive reproducibility, validation, and reliability in time-series systems, while shaping ML engineering standards and mentoring peers in a production-first environment.

Qualifications

• Strong Python software engineering skills.
• Experience productionizing ML models and monitoring pipelines.
• Hands-on with distributed data/compute platforms (Databricks or similar).
• Experience deploying workloads in containerized/service-based environments.
• Experience designing/backtesting and simulation frameworks.
• Understanding of reproducibility, validation, and reliability in time-series/event-driven systems.
• Ownership mentality with production-first engineering.
• Experience setting engineering standards and architectural decisions.
• Experience mentoring engineers and conducting code reviews.

Responsibilities

• Turn research into production-ready ML models and pipelines.
• Collaborate with data scientists to run experiments and backtest models.
• Build data/feature pipelines and ensure data lineage.
• Deploy, version, rollback, and monitor ML models in production.
• Improve runtime performance and resource utilization.
• Implement validation and safeguards before production deployment.
• Establish monitoring, drift detection, and post-mortems.
• Ensure reproducibility and explainability of historical models.

Skills

Python

Productionizing ML models

Distributed data platforms

Containerized environments

Backtesting frameworks

Reproducibility & validation

Ownership mindset

Engineering standards

Mentoring engineers

Tools

Databricks

Docker/Kubernetes

Snowflake

dbt

Java

Job description

At Eneco, we are accelerating the energy transition through our One Planet Plan, with the ambition to become climate neutral by 2035. Energy markets are becoming increasingly dynamic and complex due to renewable generation, electrification, and shifting market behavior. To operate effectively in this environment, efficient and accurate demand forecasts are essential, alongside data-driven insights on customer behavior to enable customer-fit offerings and prices.

As a Senior ML Engineer, you play a key role in building and maintaining data and ML pipelines. You will work at the intersection of data science and data engineering, helping transform ML models into reliable, scalable, and production-ready systems. These systems will drive trading decisions in the energy market, provide crucial insight for improving pricing and offerings. These insights can also identify potential improvements to business processes and guide future research. You’ll join a highly technical environment where engineering quality, ownership, and operational reliability are critical to business success.

You will work closely with data scientists to experiment with and operationalize ML models for various uses such as demand forecasting, asset detection, and market simulations. Together with data engineers, you will build the foundations that enable reliable deployment of these models and monitoring in production environments.

Your focus is turning research into robust production systems while ensuring reproducibility, validation, and observability across the ML lifecycle.

ML Model Experimentation

• Work with and enable data scientists to run experiments with ML models.
• Design, build, and maintain backtesting and experimentation frameworks.
• Ensure reproducibility across research, experimentation, and live execution environments.

Data & Feature Engineering

• Build and maintain data & feature pipelines used by ML models.
• Collaborate closely with data engineers on optimizing the structure and performance of underlying data models.
• Write technical documentation and encode explicit dependencies to enable clear data lineage & governance.
• Handle incomplete, delayed, or partial data safely in both experimentation and production environments.

Productionization & Platform Integration

• Support deployment, versioning, rollback, and release management of ML models into production-grade pipelines.
• Optimize runtime performance and resource utilization where relevant.
• Implement validation, safeguards, and operational controls before production deployment.
• Ensure stable and deterministic execution alongside other engineers.

Monitoring, Reliability & Risk Awareness

• Implement monitoring and observability for forecasting models.
• Support drift detection, anomaly monitoring, and performance degradation analysis.
• Resolve operational data incidents and conduct post-mortems.
• Ensure deterministic reruns and explainability of historical models.

Must have

• Strong software engineering skills in Python.
• Proven experience productionizing, maintaining, and monitoring ML models and pipelines.
• Hands-on experience with distributed data and compute platforms such as Databricks or similar technologies.
• Experience deploying workloads into containerized or service-based execution environments.
• Experience designing or maintaining backtesting and simulation frameworks.
• Strong understanding of reproducibility, validation, and reliability within time-series or event-driven systems.
• Strong ownership mentality with a production-first engineering mindset.
• Experience setting teamwide engineering standards and driving architectural decisions.
• Experience mentoring engineers and providing constructive review of technical designs and code.

Nice to have

• Experience with demand forecasting, energy markets, and asset detection.
• Experience with cloud-native architectures and scalable distributed systems.
• Experience collaborating closely with data scientists and data engineers.
• Experience with dbt, Snowflake, and Java

You’ll become part of a team focused on enabling accurate and efficient demand forecasting, ML experimentation, and key insights on customer behavior and trends.

The team combines expertise across data science, data engineering, data analytics, and ML engineering.

• Own the journey from ML experimentation to production - Turn forecasting and other ML models into reliable, scalable, reproducible systems that directly support trading, pricing, and customer insights.
• Shape ML engineering standards and architecture - Drive technical decisions, establish teamwide engineering standards, and mentor engineers in a highly technical, production-first environment.
• Build ML for a complex, real-world energy environment - Develop robust pipelines, backtesting frameworks, and monitoring capabilities that handle dynamic markets and incomplete or delayed data while supporting Eneco’s energy-transition ambitions.