Time Series & ML Engineering: Support the team in building, improving, and retraining machine learning forecasting models
Production Operations: Actively assist in monitoring, updating, and troubleshooting forecasting models and pipelines operating in production environments
Data Pipelines & Cleansing: Help build and maintain robust data transformation pipelines using SQLMesh and BigQuery to pre-process large streams of data
Simulation & Validation: Use our internal simulation framework to backtest forecast models and analyze how forecast errors directly impact our high-level EMS optimization yield
Agentic AI & Workflow Automation: Assist in writing, structuring, and testing behaviors for autonomous AI agents to help automate workflows
Documentation & Team Sync: Help maintain clean, clear technical documentation in Notion and collaborate with Optimization and Data Engineers during sprint cycles
Requirements
Current Studies: Enrolled in a Bachelor’s or Master’s program in Data Science, Computer Science, Statistics, Mathematics, Physics, or an equivalent quantitative field
Python Foundations: Solid coding skills in Python and familiarity with core data science libraries (pandas, numpy, scikit-learn)
ML Domain Knowledge: Solid theoretical understanding of machine learning principles, statistical analysis, model architectures (e.g., regression, tree-based ensembles), and key evaluation metrics
Analytical Mindset: Enthusiastic about troubleshooting data quality bugs and validating model outcomes using quantitative metrics
Team & Agile Mindset: You have a team-oriented mindset, enjoy working in agile environments (such as sprints), and deeply value close, transparent collaboration with your teammates
Domain Interest: A genuine interest in renewable energy, battery storage systems, smart grids, or electricity markets
Bonus points for: First touchpoints working with cloud-based infrastructure (e.g. GCP, AWS, Azure), especially containerized workflows and data warehouse solutions
SQL Literacy: Understanding of relational databases and confidence writing SQL queries for data extraction, manipulation, and aggregation.
Hands-on experience using generative AI tools, prompt engineering, or configuring AI coding assistants
Initial experience with data pipeline tools like SQLMesh or dbt. Basic understanding of visualization tools like Grafana or Looker.
Tech Stack
AWS
Azure
BigQuery
Cloud
Google Cloud Platform
Grafana
Numpy
Pandas
Python
Scikit-Learn
SQL
Benefits
You are part of an international, dynamic, and highly motivated team of people who have proven to make things happen
With your work, you accelerate the "energy transition" and hence have a direct impact on our climate
Work with and learn from other super-smart colleagues
You will enjoy direct contact with core decision-makers
You will enjoy the best chances of entering in one of Europe’s most thriving scaleups
You work remotely (Germany-wide), with offices in Hamburg, Berlin or Munich
Create a healthy balance alongside your work and enjoy all the benefits of the EGYM Wellpass