Description
Dear Consultant,
We’re looking for a highly skilled ETRM Data Scientist to join a mission-critical project in the energy trading domain. This is a remote B2B opportunity for professionals based in Poland, with a strong focus on forecasting, machine learning systems, and Azure cloud ecosystems. You will design scalable ML pipelines, optimize real-time models, and work closely with data engineering teams to ensure robust model delivery. send Cv to () if you are interested.
Key Responsibilities:
Develop scalable, reusable machine learning models for time-series forecasting and predictive analytics
Implement advanced techniques such as ARIMA, LSTM, Prophet, Linear Regression, Random Forest
Optimize, retrain, and maintain ML models based on real-world business performance and data drift
Build and automate MLOps pipelines using Python-based frameworks and Azure ML SDK
Process large-scale datasets efficiently using PySpark and Azure Databricks
Ensure model deployment, monitoring, and retraining within Azure Machine Learning environments
Required Skills & Experience:
Master’s in Mathematics, Statistics, Data Science (PhD preferred)
Extensive hands-on experience with time-series forecasting, ensemble learning, and deep learning
Proficiency in Python, scikit-learn, XGBoost, Darts, TensorFlow, PyTorch, Pandas, and NumPy
Strong knowledge of MLOps practices, including deployment automation and monitoring
Advanced Azure ML SDK usage with parallel model training and cloud orchestration
Proficiency in PySpark and large-scale data processing
Azure stack experience: Azure ML, Azure Databricks, and Azure Data Lake
Preferred Skills:
Experience with K-Means clustering, bottom-up forecasting, and Azure Data Factory
Knowledge of power trading/ETRM concepts
Exposure to Generative AI (e.g., GPT) frameworks
We’re looking for a highly skilled ETRM Data Scientist to join a mission-critical project in the energy trading domain. This is a remote B2B opportunity for professionals based in Poland, with a strong focus on forecasting, machine learning systems, and Azure cloud ecosystems. You will design scalable ML pipelines, optimize real-time models, and work closely with data engineering teams to ensure robust model delivery. send Cv to () if you are interested.
Key Responsibilities:
Develop scalable, reusable machine learning models for time-series forecasting and predictive analytics
Implement advanced techniques such as ARIMA, LSTM, Prophet, Linear Regression, Random Forest
Optimize, retrain, and maintain ML models based on real-world business performance and data drift
Build and automate MLOps pipelines using Python-based frameworks and Azure ML SDK
Process large-scale datasets efficiently using PySpark and Azure Databricks
Ensure model deployment, monitoring, and retraining within Azure Machine Learning environments
Required Skills & Experience:
Master’s in Mathematics, Statistics, Data Science (PhD preferred)
Extensive hands-on experience with time-series forecasting, ensemble learning, and deep learning
Proficiency in Python, scikit-learn, XGBoost, Darts, TensorFlow, PyTorch, Pandas, and NumPy
Strong knowledge of MLOps practices, including deployment automation and monitoring
Advanced Azure ML SDK usage with parallel model training and cloud orchestration
Proficiency in PySpark and large-scale data processing
Azure stack experience: Azure ML, Azure Databricks, and Azure Data Lake
Preferred Skills:
Experience with K-Means clustering, bottom-up forecasting, and Azure Data Factory
Knowledge of power trading/ETRM concepts
Exposure to Generative AI (e.g., GPT) frameworks