Machine Learning Engineer (Time-Series & Decision Systems)
Location: Porto (On-site)
We are building a next-generation decision intelligence platform for industrial markets.
Industrial companies operate in highly complex environments influenced by thousands of external signals-commodity prices, trade flows, energy markets, weather, geopolitics, logistics constraints, and shifting demand. Yet, many decisions are still made using spreadsheets and intuition.
Our platform identifies the most relevant signals across billions of time-series data points and transforms them into actionable, decision-ready insights.
This role sits at the intersection of machine learning, economics, and complex systems, focused on solving real-world decision-making problems under uncertainty.
What You'll Work On
Time-Series Modelling at Scale
* Commodity and chemical price dynamics
* Supply chain demand signals
* Trade flow shifts and macro indicators
* Energy and logistics cost dynamics
* Production and consumption cycles
Modelling Techniques
* ARIMA, ETS, and state-space models
* Machine learning models for time-series
* Multivariate signal discovery
* Regime detection and structural breaks
* Probabilistic forecasting
Signal Discovery
* Identify predictive relationships across datasets
* Detect causal drivers of market behavior
* Filter noise from large-scale data
Decision-Grade Forecasting
* Define decision thresholds
* Build uncertainty ranges
* Scenario simulations
* Early warning systems
Production Systems
* Feature engineering pipelines
* Scalable ML workflows
* Backtesting frameworks
* Model monitoring and evaluation
What We're Looking For
Must Have
* Strong Python skills (NumPy, pandas, scikit-learn, PyTorch or JAX)
* Solid experience in time-series modelling
* Strong problem-solving and analytical thinking
Good to Have
* Forecasting methods (ARIMA, Prophet, etc.)
* Causal inference / modelling
* Experience with large-scale datasets
* SQL, cloud platforms, and data pipelines