Lead Forecasting for Nordic Power Markets

Axpo Group; Oslo; On-site; NOK 900,000 - 1,300,000; Full time

Job summary

Axpo Group is seeking a highly quantitative forecaster to own wind, solar, demand and price forecasting across Nordic markets. You will define KPIs, monitor forecast accuracy, and lead root-cause analyses while collaborating with traders, quants, and IT.

You will develop and operate ensemble forecasting methods and ML models, ensuring live systems have robust fallback logic, and interact with external weather/forecast vendors to optimize performance.

Qualifications

• Master's degree or equivalent in physics, math/statistics, meteorology, engineering, data science or CS.
• Experience in forecasting, analytics or data science, preferably in energy/power markets.
• Strong knowledge of statistical/ML forecasting methods and time series.
• Programming in Python and SQL; Git and Azure DevOps are advantageous.
• A commercial mindset linking forecast quality to trading outcomes and risk.

Responsibilities

• Own end-to-end quality of forecasts for wind, solar, consumption and production.
• Define KPIs, monitor performance and lead root-cause analyses.
• Develop ensemble models combining internal and vendor forecasts.
• Build and run statistical/ML forecasting models with cross-team collaboration.
• Manage relationships with external forecast vendors and make buy/build decisions.
• Participate in rolling day-ahead trading, including weekends and holidays.

Skills

Forecasting

Time series analysis

Probabilistic forecasting

Ensemble methods

Python

SQL

Git

Azure DevOps

Vitec Aiolos

English

Education

Master's degree in a quantitative field

Tools

Git

Azure DevOps

Vitec Aiolos

Job description

Axpo Group is seeking a highly quantitative forecaster to own wind, solar, demand and price forecasting across Nordic markets. You will define KPIs, monitor forecast accuracy, and lead root-cause analyses while collaborating with traders, quants, and IT.

You will develop and operate ensemble forecasting methods and ML models, ensuring live systems have robust fallback logic, and interact with external weather/forecast vendors to optimize performance.